Search Results for author: Jie Yang

Found 253 papers, 90 papers with code

Exploring LLMs as a Source of Targeted Synthetic Textual Data to Minimize High Confidence Misclassifications

no code implementations26 Mar 2024 Philip Lippmann, Matthijs Spaan, Jie Yang

Natural Language Processing (NLP) models optimized for predictive performance often make high confidence errors and suffer from vulnerability to adversarial and out-of-distribution data.

Data Augmentation

Recent Advances in 3D Gaussian Splatting

no code implementations17 Mar 2024 Tong Wu, Yu-Jie Yuan, Ling-Xiao Zhang, Jie Yang, Yan-Pei Cao, Ling-Qi Yan, Lin Gao

The emergence of 3D Gaussian Splatting (3DGS) has greatly accelerated the rendering speed of novel view synthesis.

3D Reconstruction Dynamic Reconstruction +1

Generation is better than Modification: Combating High Class Homophily Variance in Graph Anomaly Detection

no code implementations15 Mar 2024 Rui Zhang, Dawei Cheng, Xin Liu, Jie Yang, Yi Ouyang, Xian Wu, Yefeng Zheng

We find that in graph anomaly detection, the homophily distribution differences between different classes are significantly greater than those in homophilic and heterophilic graphs.

Graph Anomaly Detection Graph Classification +1

Intelligent Reflecting Surfaces vs. Full-Duplex Relays: A Comparison in the Air

no code implementations14 Mar 2024 Qian Ding, Jie Yang, Yang Luo, Chunbo Luo

This letter aims to provide a fundamental analytical comparison for the two major types of relaying methods: intelligent reflecting surfaces and full-duplex relays, particularly focusing on unmanned aerial vehicle communication scenarios.

Towards the THz Networks in the 6G Era

no code implementations13 Mar 2024 Qian Ding, Jie Yang, Yang Luo, Chunbo Luo

This commentary dedicates to envision what role THz is going to play in the coming human-centric 6G era.

Body Detection

Guiding Clinical Reasoning with Large Language Models via Knowledge Seeds

no code implementations11 Mar 2024 Jiageng Wu, Xian Wu, Jie Yang

Clinical reasoning refers to the cognitive process that physicians employ in evaluating and managing patients.

Hallucination

MedKP: Medical Dialogue with Knowledge Enhancement and Clinical Pathway Encoding

no code implementations11 Mar 2024 Jiageng Wu, Xian Wu, Yefeng Zheng, Jie Yang

With appropriate data selection and training techniques, Large Language Models (LLMs) have demonstrated exceptional success in various medical examinations and multiple-choice questions.

Dialogue Generation Multiple-choice

RESTORE: Towards Feature Shift for Vision-Language Prompt Learning

1 code implementation10 Mar 2024 Yuncheng Yang, Chuyan Zhang, Zuopeng Yang, Yuting Gao, Yulei Qin, Ke Li, Xing Sun, Jie Yang, Yun Gu

Prompt learning is effective for fine-tuning foundation models to improve their generalization across a variety of downstream tasks.

Few-Shot Learning for Annotation-Efficient Nucleus Instance Segmentation

no code implementations26 Feb 2024 Yu Ming, Zihao Wu, Jie Yang, Danyi Li, Yuan Gao, Changxin Gao, Gui-Song Xia, Yuanqing Li, Li Liang, Jin-Gang Yu

In this paper, we propose to formulate annotation-efficient nucleus instance segmentation from the perspective of few-shot learning (FSL).

Few-Shot Learning Instance Segmentation +3

Higher Layers Need More LoRA Experts

1 code implementation13 Feb 2024 Chongyang Gao, Kezhen Chen, Jinmeng Rao, Baochen Sun, Ruibo Liu, Daiyi Peng, Yawen Zhang, Xiaoyuan Guo, Jie Yang, VS Subrahmanian

In this paper, we introduce a novel parameter-efficient MoE method, \textit{\textbf{M}oE-L\textbf{o}RA with \textbf{L}ayer-wise Expert \textbf{A}llocation (MoLA)} for Transformer-based models, where each model layer has the flexibility to employ a varying number of LoRA experts.

Mesh-based Gaussian Splatting for Real-time Large-scale Deformation

no code implementations7 Feb 2024 Lin Gao, Jie Yang, Bo-Tao Zhang, Jia-Mu Sun, Yu-Jie Yuan, Hongbo Fu, Yu-Kun Lai

Based on this representation, we further introduce a large-scale Gaussian deformation technique to enable deformable GS, which alters the parameters of 3D Gaussians according to the manipulation of the associated mesh.

Anything in Any Scene: Photorealistic Video Object Insertion

no code implementations30 Jan 2024 Chen Bai, Zeman Shao, Guoxiang Zhang, Di Liang, Jie Yang, Zhuorui Zhang, Yujian Guo, Chengzhang Zhong, Yiqiao Qiu, Zhendong Wang, Yichen Guan, Xiaoyin Zheng, Tao Wang, Cheng Lu

Our proposed general framework encompasses three key processes: 1) integrating a realistic object into a given scene video with proper placement to ensure geometric realism; 2) estimating the sky and environmental lighting distribution and simulating realistic shadows to enhance the light realism; 3) employing a style transfer network that refines the final video output to maximize photorealism.

Data Augmentation Object +2

Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks

1 code implementation25 Jan 2024 Tianhe Ren, Shilong Liu, Ailing Zeng, Jing Lin, Kunchang Li, He Cao, Jiayu Chen, Xinyu Huang, Yukang Chen, Feng Yan, Zhaoyang Zeng, Hao Zhang, Feng Li, Jie Yang, Hongyang Li, Qing Jiang, Lei Zhang

We introduce Grounded SAM, which uses Grounding DINO as an open-set object detector to combine with the segment anything model (SAM).

Segmentation

Learn What You Need in Personalized Federated Learning

1 code implementation16 Jan 2024 Kexin Lv, Rui Ye, Xiaolin Huang, Jie Yang, Siheng Chen

Personalized federated learning aims to address data heterogeneity across local clients in federated learning.

Image Classification Personalized Federated Learning

Dynamic Weighted Adversarial Learning for Semi-Supervised Classification under Intersectional Class Mismatch

1 code implementation ACM Transactions on Multimedia Computing, Communications, and Applications 2024 Mingyu Li, Tao Zhou, Zhuo Huang, Jian Yang, Jie Yang, Chen Gong

Nowadays, class-mismatch problem has drawn intensive attention in Semi-Supervised Learning (SSL), where the classes of labeled data are assumed to be only a subset of the classes of unlabeled data.

Domain Adaptation

Contrastive learning-based agent modeling for deep reinforcement learning

no code implementations30 Dec 2023 Wenhao Ma, Yu-Cheng Chang, Jie Yang, Yu-Kai Wang, Chin-Teng Lin

However, existing agent modeling approaches typically assume the availability of local observations from other agents (modeled agents) during training or a long observation trajectory for policy adaption.

Contrastive Learning reinforcement-learning

Red Teaming for Large Language Models At Scale: Tackling Hallucinations on Mathematics Tasks

1 code implementation30 Dec 2023 Aleksander Buszydlik, Karol Dobiczek, Michał Teodor Okoń, Konrad Skublicki, Philip Lippmann, Jie Yang

We consider the problem of red teaming LLMs on elementary calculations and algebraic tasks to evaluate how various prompting techniques affect the quality of outputs.

Dynamic In-Context Learning from Nearest Neighbors for Bundle Generation

no code implementations26 Dec 2023 Zhu Sun, Kaidong Feng, Jie Yang, Xinghua Qu, Hui Fang, Yew-Soon Ong, Wenyuan Liu

To enhance reliability and mitigate the hallucination issue, we develop (1) a self-correction strategy to foster mutual improvement in both tasks without supervision signals; and (2) an auto-feedback mechanism to recurrently offer dynamic supervision based on the distinct mistakes made by ChatGPT on various neighbor sessions.

Hallucination In-Context Learning +2

PnPNet: Pull-and-Push Networks for Volumetric Segmentation with Boundary Confusion

1 code implementation13 Dec 2023 Xin You, Ming Ding, Minghui Zhang, Hanxiao Zhang, Yi Yu, Jie Yang, Yun Gu

Precise boundary segmentation of volumetric images is a critical task for image-guided diagnosis and computer-assisted intervention, especially for boundary confusion in clinical practice.

SRSNetwork: Siamese Reconstruction-Segmentation Networks based on Dynamic-Parameter Convolution

1 code implementation4 Dec 2023 Bingkun Nian, Fenghe Tang, Jianrui Ding, Pingping Zhang, Jie Yang, S. Kevin Zhou, Wei Liu

In this paper, we present a high-performance deep neural network for weak target image segmentation, including medical image segmentation and infrared image segmentation.

Image Segmentation Medical Image Segmentation +2

MobileUtr: Revisiting the relationship between light-weight CNN and Transformer for efficient medical image segmentation

1 code implementation4 Dec 2023 Fenghe Tang, Bingkun Nian, Jianrui Ding, Quan Quan, Jie Yang, Wei Liu, S. Kevin Zhou

This work revisits the relationship between CNNs and Transformers in lightweight universal networks for medical image segmentation, aiming to integrate the advantages of both worlds at the infrastructure design level.

Image Segmentation Inductive Bias +3

TIDE: Test Time Few Shot Object Detection

1 code implementation30 Nov 2023 Weikai Li, Hongfeng Wei, Yanlai Wu, Jie Yang, Yudi Ruan, Yuan Li, Ying Tang

Few-shot object detection (FSOD) aims to extract semantic knowledge from limited object instances of novel categories within a target domain.

Data Augmentation Few-Shot Object Detection +3

Low-Dimensional Gradient Helps Out-of-Distribution Detection

no code implementations26 Oct 2023 Yingwen Wu, Tao Li, Xinwen Cheng, Jie Yang, Xiaolin Huang

To bridge this gap, in this paper, we conduct a comprehensive investigation into leveraging the entirety of gradient information for OOD detection.

Dimensionality Reduction Out-of-Distribution Detection

Revisiting Deep Ensemble for Out-of-Distribution Detection: A Loss Landscape Perspective

1 code implementation22 Oct 2023 Kun Fang, Qinghua Tao, Xiaolin Huang, Jie Yang

Motivated by such diversities on OoD loss landscape across modes, we revisit the deep ensemble method for OoD detection through mode ensemble, leading to improved performance and benefiting the OoD detector with reduced variances.

Out-of-Distribution Detection Out of Distribution (OOD) Detection

UniPose: Detecting Any Keypoints

1 code implementation12 Oct 2023 Jie Yang, Ailing Zeng, Ruimao Zhang, Lei Zhang

This work proposes a unified framework called UniPose to detect keypoints of any articulated (e. g., human and animal), rigid, and soft objects via visual or textual prompts for fine-grained vision understanding and manipulation.

 Ranked #1 on 2D Human Pose Estimation on Human-Art (using extra training data)

2D Human Pose Estimation 2D Pose Estimation +4

ClusVPR: Efficient Visual Place Recognition with Clustering-based Weighted Transformer

no code implementations6 Oct 2023 Yifan Xu, Pourya Shamsolmoali, Jie Yang

VPR is particularly difficult due to the presence of duplicate regions and the lack of attention to small objects in complex scenes, resulting in recognition deviations.

Clustering Robot Navigation +1

Semantic Difference Guidance for the Uncertain Boundary Segmentation of CT Left Atrial Appendage

1 code implementation MICCAI 2023 Xin You, Ming Ding, Minghui Zhang, Yangqian Wu, Yi Yu, Yun Gu, Jie Yang

In this paper, we have modeled relative relations between the LA and LAA via deep segmentation networks for the first time, and introduce a new LA & LAA CT dataset.

Segmentation

MMA-Net: Multiple Morphology-Aware Network for Automated Cobb Angle Measurement

no code implementations25 Sep 2023 Zhengxuan Qiu, Jie Yang, Jiankun Wang

In the MMA-Net, we first feed spine X-ray images into the segmentation network to produce multiple morphological information (spine region, centerline, and boundary) and then concatenate the original X-ray image with the resulting segmentation maps as input for the regression module to perform precise Cobb angle measurement.

regression Segmentation

Towards Better Data Exploitation in Self-Supervised Monocular Depth Estimation

1 code implementation11 Sep 2023 Jinfeng Liu, Lingtong Kong, Jie Yang, Wei Liu

Additionally, we introduce the detail-enhanced DepthNet with an extra full-scale branch in the encoder and a grid decoder to enhance the restoration of fine details in depth maps.

Data Augmentation Monocular Depth Estimation

Dynamic Frame Interpolation in Wavelet Domain

1 code implementation7 Sep 2023 Lingtong Kong, Boyuan Jiang, Donghao Luo, Wenqing Chu, Ying Tai, Chengjie Wang, Jie Yang

Video frame interpolation is an important low-level vision task, which can increase frame rate for more fluent visual experience.

Optical Flow Estimation Video Frame Interpolation

Neural Network-Based Histologic Remission Prediction In Ulcerative Colitis

no code implementations28 Aug 2023 Yemin li, Zhongcheng Liu, Xiaoying Lou, Mirigual Kurban, Miao Li, Jie Yang, Kaiwei Che, Jiankun Wang, Max Q. -H Meng, Yan Huang, Qin Guo, Pinjin Hu

A total of 5105 images of 154 intestinal segments from 87 patients undergoing EC treatment at a center in China between March 2022 and March 2023 are scored according to the Geboes score.

Specificity

ARTIST: ARTificial Intelligence for Simplified Text

1 code implementation25 Aug 2023 Lorenzo Corti, Jie Yang

Complex text is a major barrier for many citizens when accessing public information and knowledge.

Text Simplification

Neural Interactive Keypoint Detection

1 code implementation ICCV 2023 Jie Yang, Ailing Zeng, Feng Li, Shilong Liu, Ruimao Zhang, Lei Zhang

Click-Pose explores how user feedback can cooperate with a neural keypoint detector to correct the predicted keypoints in an interactive way for a faster and more effective annotation process.

Keypoint Detection

Tackling Vision Language Tasks Through Learning Inner Monologues

no code implementations19 Aug 2023 Diji Yang, Kezhen Chen, Jinmeng Rao, Xiaoyuan Guo, Yawen Zhang, Jie Yang, Yi Zhang

Visual language tasks require AI models to comprehend and reason with both visual and textual content.

MC-DRE: Multi-Aspect Cross Integration for Drug Event/Entity Extraction

1 code implementation12 Aug 2023 Jie Yang, Soyeon Caren Han, Siqu Long, Josiah Poon, Goran Nenadic

Extracting meaningful drug-related information chunks, such as adverse drug events (ADE), is crucial for preventing morbidity and saving many lives.

Event Detection Event Extraction +4

Pick the Best Pre-trained Model: Towards Transferability Estimation for Medical Image Segmentation

1 code implementation22 Jul 2023 Yuncheng Yang, Meng Wei, Junjun He, Jie Yang, Jin Ye, Yun Gu

To make up for its deficiency when applying transfer learning to medical image segmentation, in this paper, we therefore propose a new Transferability Estimation (TE) method.

Image Segmentation Medical Image Segmentation +3

Streamlining Social Media Information Retrieval for COVID-19 Research with Deep Learning

2 code implementations28 Jun 2023 Yining Hua, Jiageng Wu, Shixu Lin, Minghui Li, Yujie Zhang, Dinah Foer, Siwen Wang, Peilin Zhou, Jie Yang, Li Zhou

Conclusions: This study advances public health research by implementing a novel, systematic pipeline for curating symptom lexicons from social media data.

Information Retrieval named-entity-recognition +3

A Novel Dual-pooling Attention Module for UAV Vehicle Re-identification

no code implementations25 Jun 2023 Xiaoyan Guo, Jie Yang, Xinyu Jia, Chuanyan Zang, Yan Xu, Zhaoyang Chen

Therefore, this paper proposes a novel dual-pooling attention (DpA) module, which achieves the extraction and enhancement of locally important information about vehicles from both channel and spatial dimensions by constructing two branches of channel-pooling attention (CpA) and spatial-pooling attention (SpA), and employing multiple pooling operations to enhance the attention to fine-grained information of vehicles.

Single Particle Analysis Vehicle Re-Identification

detrex: Benchmarking Detection Transformers

1 code implementation12 Jun 2023 Tianhe Ren, Shilong Liu, Feng Li, Hao Zhang, Ailing Zeng, Jie Yang, Xingyu Liao, Ding Jia, Hongyang Li, He Cao, Jianan Wang, Zhaoyang Zeng, Xianbiao Qi, Yuhui Yuan, Jianwei Yang, Lei Zhang

To address this issue, we develop a unified, highly modular, and lightweight codebase called detrex, which supports a majority of the mainstream DETR-based instance recognition algorithms, covering various fundamental tasks, including object detection, segmentation, and pose estimation.

Benchmarking object-detection +2

LOWA: Localize Objects in the Wild with Attributes

no code implementations31 May 2023 Xiaoyuan Guo, Kezhen Chen, Jinmeng Rao, Yawen Zhang, Baochen Sun, Jie Yang

To train LOWA, we propose a hybrid vision-language training strategy to learn object detection and recognition with class names as well as attribute information.

Attribute Object +3

Boosting Human-Object Interaction Detection with Text-to-Image Diffusion Model

1 code implementation20 May 2023 Jie Yang, Bingliang Li, Fengyu Yang, Ailing Zeng, Lei Zhang, Ruimao Zhang

Extensive experiments demonstrate that DiffHOI significantly outperforms the state-of-the-art in regular detection (i. e., 41. 50 mAP) and zero-shot detection.

Ranked #2 on Zero-Shot Human-Object Interaction Detection on HICO-DET (using extra training data)

Human-Object Interaction Detection Zero-Shot Human-Object Interaction Detection

NeUDF: Leaning Neural Unsigned Distance Fields with Volume Rendering

no code implementations CVPR 2023 Yu-Tao Liu, Li Wang, Jie Yang, Weikai Chen, Xiaoxu Meng, Bo Yang, Lin Gao

Multi-view shape reconstruction has achieved impressive progresses thanks to the latest advances in neural implicit surface rendering.

Neural Rendering Surface Reconstruction +1

CDFI: Cross Domain Feature Interaction for Robust Bronchi Lumen Detection

no code implementations18 Apr 2023 Jiasheng Xu, Tianyi Zhang, Yangqian Wu, Jie Yang, Guang-Zhong Yang, Yun Gu

Endobronchial intervention is increasingly used as a minimally invasive means for the treatment of pulmonary diseases.

RF-GNN: Random Forest Boosted Graph Neural Network for Social Bot Detection

1 code implementation14 Apr 2023 Shuhao Shi, Kai Qiao, Jie Yang, Baojie Song, Jian Chen, Bin Yan

This paper proposes a Random Forest boosted Graph Neural Network for social bot detection, called RF-GNN, which employs graph neural networks (GNNs) as the base classifiers to construct a random forest, effectively combining the advantages of ensemble learning and GNNs to improve the accuracy and robustness of the model.

Ensemble Learning feature selection +1

Semantic Human Parsing via Scalable Semantic Transfer over Multiple Label Domains

no code implementations CVPR 2023 Jie Yang, Chaoqun Wang, Zhen Li, Junle Wang, Ruimao Zhang

This paper presents Scalable Semantic Transfer (SST), a novel training paradigm, to explore how to leverage the mutual benefits of the data from different label domains (i. e. various levels of label granularity) to train a powerful human parsing network.

Human Parsing Representation Learning

Learning with Explicit Shape Priors for Medical Image Segmentation

1 code implementation31 Mar 2023 Xin You, Junjun He, Jie Yang, Yun Gu

Hence, in our work, we proposed a novel shape prior module (SPM), which can explicitly introduce shape priors to promote the segmentation performance of UNet-based models.

Image Segmentation Medical Image Segmentation +2

SoftCLIP: Softer Cross-modal Alignment Makes CLIP Stronger

no code implementations30 Mar 2023 Yuting Gao, Jinfeng Liu, Zihan Xu, Tong Wu Enwei Zhang, Wei Liu, Jie Yang, Ke Li, Xing Sun

During the preceding biennium, vision-language pre-training has achieved noteworthy success on several downstream tasks.

Zero-Shot Learning

Inherent Consistent Learning for Accurate Semi-supervised Medical Image Segmentation

2 code implementations24 Mar 2023 Ye Zhu, Jie Yang, Si-Qi Liu, Ruimao Zhang

Semi-supervised medical image segmentation has attracted much attention in recent years because of the high cost of medical image annotations.

Image Segmentation Segmentation +2

Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection

5 code implementations9 Mar 2023 Shilong Liu, Zhaoyang Zeng, Tianhe Ren, Feng Li, Hao Zhang, Jie Yang, Chunyuan Li, Jianwei Yang, Hang Su, Jun Zhu, Lei Zhang

To effectively fuse language and vision modalities, we conceptually divide a closed-set detector into three phases and propose a tight fusion solution, which includes a feature enhancer, a language-guided query selection, and a cross-modality decoder for cross-modality fusion.

Referring Expression Referring Expression Comprehension +2

Exploring Social Media for Early Detection of Depression in COVID-19 Patients

1 code implementation23 Feb 2023 Jiageng Wu, Xian Wu, Yining Hua, Shixu Lin, Yefeng Zheng, Jie Yang

Secondly, We conducted an extensive analysis of this dataset to investigate the characteristic of COVID-19 patients with a higher risk of depression.

Knowledge Distillation

SceneHGN: Hierarchical Graph Networks for 3D Indoor Scene Generation with Fine-Grained Geometry

no code implementations16 Feb 2023 Lin Gao, Jia-Mu Sun, Kaichun Mo, Yu-Kun Lai, Leonidas J. Guibas, Jie Yang

We propose SCENEHGN, a hierarchical graph network for 3D indoor scenes that takes into account the full hierarchy from the room level to the object level, then finally to the object part level.

Scene Generation

Over-Sampling Strategy in Feature Space for Graphs based Class-imbalanced Bot Detection

1 code implementation14 Feb 2023 Shuhao Shi, Kai Qiao, Jie Yang, Baojie Song, Jian Chen, Bin Yan

The proposed framework is evaluated using three real-world bot detection benchmark datasets, and it consistently exhibits superiority over the baselines.

Eliminating Contextual Prior Bias for Semantic Image Editing via Dual-Cycle Diffusion

1 code implementation5 Feb 2023 Zuopeng Yang, Tianshu Chu, Xin Lin, Erdun Gao, Daqing Liu, Jie Yang, Chaoyue Wang

The proposed model incorporates a Bias Elimination Cycle that consists of both a forward path and an inverted path, each featuring a Structural Consistency Cycle to ensure the preservation of image content during the editing process.

Text-to-Image Generation

Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimation

3 code implementations3 Feb 2023 Jie Yang, Ailing Zeng, Shilong Liu, Feng Li, Ruimao Zhang, Lei Zhang

This paper presents a novel end-to-end framework with Explicit box Detection for multi-person Pose estimation, called ED-Pose, where it unifies the contextual learning between human-level (global) and keypoint-level (local) information.

2D Human Pose Estimation Human Detection +3

Shorter Latency of Real-time Epileptic Seizure Detection via Probabilistic Prediction

no code implementations4 Jan 2023 Yankun Xu, Jie Yang, Wenjie Ming, Shuang Wang, Mohamad Sawan

And, a novel multiscale STFT-based feature extraction method combined with 3D-CNN architecture is proposed to accurately capture predictive probabilities of samples.

Binary Classification Decision Making +3

MGTAB: A Multi-Relational Graph-Based Twitter Account Detection Benchmark

1 code implementation3 Jan 2023 Shuhao Shi, Kai Qiao, Jian Chen, Shuai Yang, Jie Yang, Baojie Song, Linyuan Wang, Bin Yan

However, in addition to low annotation quality, existing benchmarks generally have incomplete user relationships, suppressing graph-based account detection research.

Node Classification Stance Detection +1

FoPro: Few-Shot Guided Robust Webly-Supervised Prototypical Learning

1 code implementation1 Dec 2022 Yulei Qin, Xingyu Chen, Chao Chen, Yunhang Shen, Bo Ren, Yun Gu, Jie Yang, Chunhua Shen

Most existing methods focus on learning noise-robust models from web images while neglecting the performance drop caused by the differences between web domain and real-world domain.

Contrastive Learning Representation Learning

A 97 fJ/Conversion Neuron-ADC with Reconfigurable Sampling and Static Power Reduction

no code implementations28 Nov 2022 Jinbo Chen, Hui Wu, Jie Yang, Mohamad Sawan

A bio-inspired Neuron-ADC with reconfigurable sampling and static power reduction for biomedical applications is proposed in this work.

Sub-1ms Instinctual Interference Adaptive GaN LNA Front-End with Power and Linearity Tuning

no code implementations27 Nov 2022 Jie Yang, Baibhab Chatterjee, Mohammad Abu Khater, Mattias Thorsell, Sten E. Gunnarsson, Tero Kiuru, Shreyas Sen

The system permits an LNA power consumption to tune from 500 mW to 2 W (4X increase) in order to adjust the linearity from P\textsubscript{1dB, IN}=-10. 5 dBm to 0. 5 dBm (>10X increase).

On Multi-head Ensemble of Smoothed Classifiers for Certified Robustness

1 code implementation20 Nov 2022 Kun Fang, Qinghua Tao, Yingwen Wu, Tao Li, Xiaolin Huang, Jie Yang

Randomized Smoothing (RS) is a promising technique for certified robustness, and recently in RS the ensemble of multiple deep neural networks (DNNs) has shown state-of-the-art performances.

GreenPLM: Cross-Lingual Transfer of Monolingual Pre-Trained Language Models at Almost No Cost

1 code implementation13 Nov 2022 Qingcheng Zeng, Lucas Garay, Peilin Zhou, Dading Chong, Yining Hua, Jiageng Wu, Yikang Pan, Han Zhou, Rob Voigt, Jie Yang

Large pre-trained models have revolutionized natural language processing (NLP) research and applications, but high training costs and limited data resources have prevented their benefits from being shared equally amongst speakers of all the world's languages.

Cross-Lingual Transfer

MDFlow: Unsupervised Optical Flow Learning by Reliable Mutual Knowledge Distillation

1 code implementation11 Nov 2022 Lingtong Kong, Jie Yang

To break the dilemma, we propose a novel mutual distillation framework to transfer reliable knowledge back and forth between the teacher and student networks for alternate improvement.

Blocking Data Augmentation +2

Progressive Motion Context Refine Network for Efficient Video Frame Interpolation

no code implementations11 Nov 2022 Lingtong Kong, Jinfeng Liu, Jie Yang

Recently, flow-based frame interpolation methods have achieved great success by first modeling optical flow between target and input frames, and then building synthesis network for target frame generation.

Optical Flow Estimation Video Frame Interpolation

AI enhanced finite element multiscale modelling and structural uncertainty analysis of a functionally graded porous beam

no code implementations2 Nov 2022 Da Chen, Nima Emami, Shahed Rezaei, Philipp L. Rosendahl, Bai-Xiang Xu, Jens Schneider, Kang Gao, Jie Yang

The error range of CNN models leads to an uncertain mechanical performance, which is further evaluated in a structural uncertainty analysis on the FG porous three-layer beam consisting of two thin high-density layers and a thick low-density one, where the imprecise CNN predicted moduli are represented as triangular fuzzy numbers in double parametric form.

3D Human Mesh Construction Leveraging Wi-Fi

no code implementations20 Oct 2022 Yichao Wang, Jie Yang

In this paper, we present, Wi-Mesh, a WiFi vision-based 3D human mesh construction system.

Online LiDAR-Camera Extrinsic Parameters Self-checking

1 code implementation19 Oct 2022 Pengjin Wei, Guohang Yan, Yikang Li, Kun Fang, Jie Yang, Wei Liu

This calibration task is multi-modal, where the rich color and texture information captured by the camera and the accurate three-dimensional spatial information from the LiDAR is incredibly significant for downstream tasks.

Autonomous Driving Binary Classification

A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities

1 code implementation17 Oct 2022 Andrea Tocchetti, Lorenzo Corti, Agathe Balayn, Mireia Yurrita, Philip Lippmann, Marco Brambilla, Jie Yang

Despite the impressive performance of Artificial Intelligence (AI) systems, their robustness remains elusive and constitutes a key issue that impedes large-scale adoption.

Survey of Deep Learning for Autonomous Surface Vehicles in the Marine Environment

no code implementations16 Oct 2022 Yuanyuan Qiao, Jiaxin Yin, Wei Wang, Fábio Duarte, Jie Yang, Carlo Ratti

Within the next several years, there will be a high level of autonomous technology that will be available for widespread use, which will reduce labor costs, increase safety, save energy, enable difficult unmanned tasks in harsh environments, and eliminate human error.

Autonomous Vehicles Self-Learning

Transfer Learning on Electromyography (EMG) Tasks: Approaches and Beyond

no code implementations3 Oct 2022 Di wu, Jie Yang, Mohamad Sawan

In this survey, we assess the eligibility of more than fifty published peer-reviewed representative transfer learning approaches for EMG applications.

Electromyography (EMG) Transfer Learning

Robust Person Identification: A WiFi Vision-based Approach

no code implementations30 Sep 2022 Yili Ren, Jie Yang

In particular, we leverage multiple antennas on next-generation WiFi devices and 2D AoA estimation of the signal reflections to enable WiFi to visualize a person in the physical environment.

Person Identification Person Re-Identification

Rethinking and Recomputing the Value of ML Models

no code implementations30 Sep 2022 Burcu Sayin, Fabio Casati, Andrea Passerini, Jie Yang, Xinyue Chen

In this paper, we argue that the way we have been training and evaluating ML models has largely forgotten the fact that they are applied in an organization or societal context as they provide value to people.

METS-CoV: A Dataset of Medical Entity and Targeted Sentiment on COVID-19 Related Tweets

1 code implementation28 Sep 2022 Peilin Zhou, Zeqiang Wang, Dading Chong, Zhijiang Guo, Yining Hua, Zichang Su, Zhiyang Teng, Jiageng Wu, Jie Yang

To further investigate tweet users' attitudes toward specific entities, 4 types of entities (Person, Organization, Drug, and Vaccine) are selected and annotated with user sentiments, resulting in a targeted sentiment dataset with 9, 101 entities (in 5, 278 tweets).

Epidemiology named-entity-recognition +3

YATO: Yet Another deep learning based Text analysis Open toolkit

1 code implementation28 Sep 2022 Zeqiang Wang, Yile Wang, Jiageng Wu, Zhiyang Teng, Jie Yang

Designed in a hierarchical structure, YATO supports free combinations of three types of widely used features including 1) traditional neural networks (CNN, RNN, etc.

A Compact Online-Learning Spiking Neuromorphic Biosignal Processor

no code implementations26 Sep 2022 Chaoming Fang, Ziyang Shen, Fengshi Tian, Jie Yang, Mohamad Sawan

In this design, a compact online learning neuromorphic hardware architecture with ultra-low power consumption designed explicitly for biosignal processing is proposed.

ECG Classification

SpikeSEE: An Energy-Efficient Dynamic Scenes Processing Framework for Retinal Prostheses

no code implementations16 Sep 2022 Chuanqing Wang, Chaoming Fang, Yong Zou, Jie Yang, Mohamad Sawan

In this paper, we propose an energy-efficient dynamic scenes processing framework (SpikeSEE) that combines a spike representation encoding technique and a bio-inspired spiking recurrent neural network (SRNN) model to achieve intelligent processing and extreme low-power computation for retinal prostheses.

PTab: Using the Pre-trained Language Model for Modeling Tabular Data

no code implementations15 Sep 2022 Guang Liu, Jie Yang, Ledell Wu

The learning of an effective contextual representation requires meaningful features and a large amount of data.

Language Modelling Representation Learning +1

An Online Sparse Streaming Feature Selection Algorithm

no code implementations2 Aug 2022 Feilong Chen, Di wu, Jie Yang, Yi He

In many real applications such as intelligent healthcare platform, streaming feature always has some missing data, which raises a crucial challenge in conducting OSFS, i. e., how to establish the uncertain relationship between sparse streaming features and labels.

feature selection

Personalized Promotion Decision Making Based on Direct and Enduring Effect Predictions

no code implementations23 Jul 2022 Jie Yang, Yilin Li, Deddy Jobson

To achieve a better lift return on investment (lift ROI) on the enduring effect of the promotion and improve customer retention and loyalty, we propose a framework of multiple treatment promotion decision making by modeling each customer's direct and enduring response.

Decision Making

Using Twitter Data to Understand Public Perceptions of Approved versus Off-label Use for COVID-19-related Medications

1 code implementation29 Jun 2022 Yining Hua, Hang Jiang, Shixu Lin, Jie Yang, Joseph M. Plasek, David W. Bates, Li Zhou

Time-trend analysis indicated that Hydroxychloroquine and Ivermectin were discussed more than Molnupiravir and Remdesivir, particularly during COVID-19 surges.

Misinformation

Learning Deep Feature Correspondence for Unsupervised Anomaly Detection and Segmentation

1 code implementation Pattetn Recognition 2022 Jie Yang

We develop our DFC in an asymmetric dual network framework that consists of a generic feature extraction network and an elaborated feature estimation network, and detect the possible anomalies within images by modeling and evaluating the associated deep feature correspondence between the two dual network branches.

 Ranked #1 on Anomaly Detection on BottleCap (using extra training data)

Unsupervised Anomaly Detection

Toward Clinically Assisted Colorectal Polyp Recognition via Structured Cross-modal Representation Consistency

1 code implementation23 Jun 2022 Weijie Ma, Ye Zhu, Ruimao Zhang, Jie Yang, Yiwen Hu, Zhen Li, Li Xiang

By aligning the class tokens and spatial attention maps of paired NBI and WL images at different levels, the Transformer achieves the ability to keep both global and local representation consistency for the above two modalities.

Classification Image Classification

DaisyRec 2.0: Benchmarking Recommendation for Rigorous Evaluation

2 code implementations22 Jun 2022 Zhu Sun, Hui Fang, Jie Yang, Xinghua Qu, Hongyang Liu, Di Yu, Yew-Soon Ong, Jie Zhang

Recently, one critical issue looms large in the field of recommender systems -- there are no effective benchmarks for rigorous evaluation -- which consequently leads to unreproducible evaluation and unfair comparison.

Benchmarking Recommendation Systems

AMOS: A Large-Scale Abdominal Multi-Organ Benchmark for Versatile Medical Image Segmentation

1 code implementation16 Jun 2022 Yuanfeng Ji, Haotian Bai, Jie Yang, Chongjian Ge, Ye Zhu, Ruimao Zhang, Zhen Li, Lingyan Zhang, Wanling Ma, Xiang Wan, Ping Luo

Constraint by the high cost of collecting and labeling 3D medical data, most of the deep learning models to date are driven by datasets with a limited number of organs of interest or samples, which still limits the power of modern deep models and makes it difficult to provide a fully comprehensive and fair estimate of various methods.

Image Segmentation Medical Image Segmentation +3

Binary Single-dimensional Convolutional Neural Network for Seizure Prediction

no code implementations8 Jun 2022 Shiqi Zhao, Jie Yang, Yankun Xu, Mohamad Sawan

Nowadays, several deep learning methods are proposed to tackle the challenge of epileptic seizure prediction.

EEG Electroencephalogram (EEG) +1

Modeling Image Composition for Complex Scene Generation

1 code implementation CVPR 2022 Zuopeng Yang, Daqing Liu, Chaoyue Wang, Jie Yang, DaCheng Tao

Compared to existing CNN-based and Transformer-based generation models that entangled modeling on pixel-level&patch-level and object-level&patch-level respectively, the proposed focal attention predicts the current patch token by only focusing on its highly-related tokens that specified by the spatial layout, thereby achieving disambiguation during training.

Layout-to-Image Generation Object +1

IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation

2 code implementations CVPR 2022 Lingtong Kong, Boyuan Jiang, Donghao Luo, Wenqing Chu, Xiaoming Huang, Ying Tai, Chengjie Wang, Jie Yang

Prevailing video frame interpolation algorithms, that generate the intermediate frames from consecutive inputs, typically rely on complex model architectures with heavy parameters or large delay, hindering them from diverse real-time applications.

Optical Flow Estimation Video Frame Interpolation

Recent Trends and Future Prospects of Neural Recording Circuits and Systems: A Tutorial Brief

no code implementations27 May 2022 Jinbo Chen, Mahdi Tarkhan, Hui Wu, Fereidoon Hashemi Noshahr, Jie Yang, Mohamad Sawan

Recent years have seen fast advances in neural recording circuits and systems as they offer a promising way to investigate real-time brain monitoring and the closed-loop modulation of psychological disorders and neurodegenerative diseases.

An Event-Driven Compressive Neuromorphic System for Cardiac Arrhythmia Detection

no code implementations26 May 2022 Jinbo Chen, Fengshi Tian, Jie Yang, Mohamad Sawan

Wearable electrocardiograph (ECG) recording and processing systems have been developed to detect cardiac arrhythmia to help prevent heart attacks.

Arrhythmia Detection

Enhanced Single-shot Detector for Small Object Detection in Remote Sensing Images

no code implementations12 May 2022 Pourya Shamsolmoali, Masoumeh Zareapoor, Eric Granger, Jocelyn Chanussot, Jie Yang

In IPSSD, single-shot detector is adopted combined with an image pyramid network to extract semantically strong features for generating candidate regions.

Object object-detection +1

Multichannel Synthetic Preictal EEG Signals to Enhance the Prediction of Epileptic Seizures

no code implementations29 Apr 2022 Yankun Xu, Jie Yang, Mohamad Sawan

To identify the preictal region that precedes the onset of seizure, a large number of annotated EEG signals are required to train DL algorithms.

EEG Electroencephalogram (EEG) +1

neuro2vec: Masked Fourier Spectrum Prediction for Neurophysiological Representation Learning

1 code implementation20 Apr 2022 Di wu, Siyuan Li, Jie Yang, Mohamad Sawan

Extensive data labeling on neurophysiological signals is often prohibitively expensive or impractical, as it may require particular infrastructure or domain expertise.

EEG Electroencephalogram (EEG) +3

3D Human Pose Estimation for Free-from and Moving Activities Using WiFi

no code implementations16 Apr 2022 Yili Ren, Jie Yang

This paper presents GoPose, a 3D skeleton-based human pose estimation system that uses WiFi devices at home.

3D Human Pose Estimation 3D Pose Estimation +1

Towards Fine-grained Causal Reasoning and QA

1 code implementation15 Apr 2022 Linyi Yang, Zhen Wang, Yuxiang Wu, Jie Yang, Yue Zhang

Understanding causality is key to the success of NLP applications, especially in high-stakes domains.

Question Answering Sentence

Bridging the Gap Between Patient-specific and Patient-independent Seizure Prediction via Knowledge Distillation

no code implementations25 Feb 2022 Di wu, Jie Yang, Mohamad Sawan

The proposed training scheme significantly improves the performance of patient-specific seizure predictors and bridges the gap between patient-specific and patient-independent predictors.

Knowledge Distillation Seizure prediction

Online Learning of Trellis Diagram Using Neural Network for Robust Detection and Decoding

no code implementations22 Feb 2022 Jie Yang, Qinghe Du, Yi Jiang

As an interesting by-product, we propose an enhancement to the BLE standard by introducing a bit interleaver to its physical layer; the resultant improvement of the receiver sensitivity can make it a better fit for some Internet of Things (IoT) communications.

Anchor Graph Structure Fusion Hashing for Cross-Modal Similarity Search

no code implementations9 Feb 2022 Lu Wang, Jie Yang, Masoumeh Zareapoor, ZhongLong Zheng

Cross-modal hashing still has some challenges needed to address: (1) most existing CMH methods take graphs as input to model data distribution.

Retrieval

BREAK: Bronchi Reconstruction by gEodesic transformation And sKeleton embedding

no code implementations29 Jan 2022 Weihao Yu, Hao Zheng, Minghui Zhang, Hanxiao Zhang, Jiayuan Sun, Jie Yang

Since the volume of the peripheral bronchi may be much smaller than the large branches in an input patch, the common segmentation loss is not sensitive to the breakages among the distal branches.

Segmentation

On the Value of ML Models

no code implementations13 Dec 2021 Fabio Casati, Pierre-André Noël, Jie Yang

We argue that, when establishing and benchmarking Machine Learning (ML) models, the research community should favour evaluation metrics that better capture the value delivered by their model in practical applications.

Benchmarking

The Science of Rejection: A Research Area for Human Computation

no code implementations11 Nov 2021 Burcu Sayin, Jie Yang, Andrea Passerini, Fabio Casati

We motivate why the science of learning to reject model predictions is central to ML, and why human computation has a lead role in this effort.

OctField: Hierarchical Implicit Functions for 3D Modeling

no code implementations NeurIPS 2021 Jia-Heng Tang, Weikai Chen, Jie Yang, Bo wang, Songrun Liu, Bo Yang, Lin Gao

We achieve this goal by introducing a hierarchical octree structure to adaptively subdivide the 3D space according to the surface occupancy and the richness of part geometry.

C$^2$SP-Net: Joint Compression and Classification Network for Epilepsy Seizure Prediction

no code implementations26 Oct 2021 Di wu, Yi Shi, Ziyu Wang, Jie Yang, Mohamad Sawan

Although compressive sensing (CS) can be adopted to compress the signals to reduce communication bandwidth requirement, it needs a complex reconstruction procedure before the signal can be used for seizure prediction.

Compressive Sensing Seizure prediction

Osteoporosis Prescreening using Panoramic Radiographs through a Deep Convolutional Neural Network with Attention Mechanism

no code implementations19 Oct 2021 Heng Fan, Jiaxiang Ren, Jie Yang, Yi-Xian Qin, Haibin Ling

The aim of this study was to investigate whether a deep convolutional neural network (CNN) with an attention module can detect osteoporosis on panoramic radiographs.

AEFE: Automatic Embedded Feature Engineering for Categorical Features

no code implementations19 Oct 2021 Zhenyuan Zhong, Jie Yang, Yacong Ma, Shoubin Dong, Jinlong Hu

The challenge of solving data mining problems in e-commerce applications such as recommendation system (RS) and click-through rate (CTR) prediction is how to make inferences by constructing combinatorial features from a large number of categorical features while preserving the interpretability of the method.

Click-Through Rate Prediction Feature Engineering +2

Demographic Biases of Crowd Workers in Key Opinion Leaders Finding

no code implementations18 Oct 2021 Hossein A. Rahmani, Jie Yang

Key Opinion Leaders (KOLs) are people that have a strong influence and their opinions are listened to by people when making important decisions.

counterfactual

3D Human Pose Estimation for Free-form Activity Using WiFi Signals

no code implementations15 Oct 2021 Yili Ren, Jie Yang

Our system tracks free-form activity by estimating a 3D skeleton pose that consists of a set of joints of the human body.

3D Human Pose Estimation 3D Human Pose Tracking

Context-guided Triple Matching for Multiple Choice Question Answering

no code implementations27 Sep 2021 Xun Yao, Junlong Ma, Xinrong Hu, Junping Liu, Jie Yang, Wanqing Li

The task of multiple choice question answering (MCQA) refers to identifying a suitable answer from multiple candidates, by estimating the matching score among the triple of the passage, question and answer.

Benchmarking Multiple-choice +1

Visual Anomaly Detection for Images: A Survey

no code implementations27 Sep 2021 Jie Yang, Ruijie Xu, Zhiquan Qi, Yong Shi

Visual anomaly detection is an important and challenging problem in the field of machine learning and computer vision.

Anomaly Detection

Rethinking Lightweight Convolutional Neural Networks for Efficient and High-quality Pavement Crack Detection

2 code implementations13 Sep 2021 Kai Li, Jie Yang, Siwei Ma, Bo wang, Shanshe Wang, Yingjie Tian, Zhiquan Qi

For the second issue, we reconsider how to improve detection efficiency with excellent performance, and then propose our lightweight encoder-decoder architecture termed CarNet.

N24News: A New Dataset for Multimodal News Classification

1 code implementation LREC 2022 Zhen Wang, Xu Shan, Xiangxie Zhang, Jie Yang

Current news datasets merely focus on text features on the news and rarely leverage the feature of images, excluding numerous essential features for news classification.

Classification News Classification

Multi-patch Feature Pyramid Network for Weakly Supervised Object Detection in Optical Remote Sensing Images

no code implementations18 Aug 2021 Pourya Shamsolmoali, Jocelyn Chanussot, Masoumeh Zareapoor, Huiyu Zhou, Jie Yang

Second, most of the standard methods used hand-crafted features, and do not work well on the detection of objects parts of which are missing.

Object object-detection +1

An End-to-End Deep Learning Approach for Epileptic Seizure Prediction

no code implementations17 Aug 2021 Yankun Xu, Jie Yang, Shiqi Zhao, Hemmings Wu, Mohamad Sawan

Conventional seizure prediction works usually rely on features extracted from Electroencephalography (EEG) recordings and classification algorithms such as regression or support vector machine (SVM) to locate the short time before seizure onset.

EEG Electroencephalogram (EEG) +2

A Generalized Framework for Edge-preserving and Structure-preserving Image Smoothing

1 code implementation15 Jul 2021 Wei Liu, Pingping Zhang, Yinjie Lei, Xiaolin Huang, Jie Yang, Michael Ng

The effectiveness and superior performance of our approach are validated through comprehensive experiments in a range of applications.

image smoothing

LightFuse: Lightweight CNN based Dual-exposure Fusion

1 code implementation5 Jul 2021 Ziyi Liu, Jie Yang, Svetlana Yanushkevich, Orly Yadid-Pecht

Embedded systems have a huge market, and utilizing DCNNs' powerful functionality into them will further reduce human intervention.

Relationship between pulmonary nodule malignancy and surrounding pleurae, airways and vessels: a quantitative study using the public LIDC-IDRI dataset

no code implementations24 Jun 2021 Yulei Qin, Yun Gu, Hanxiao Zhang, Jie Yang, Lihui Wang, Zhexin Wang, Feng Yao, Yue-Min Zhu

The correlation between nodules and the counting number of airways and vessels that contact or project towards nodules are respectively (OR=22. 96, \chi^2=105. 04) and (OR=7. 06, \chi^2=290. 11).

Computed Tomography (CT)

Liquid Sensing Using WiFi Signals

no code implementations18 Jun 2021 Yili Ren, Jie Yang

Among those services, sensing the liquid level in a container is critical to building many smart home and mobile healthcare applications that improve the quality of life.

supervised adptive threshold network for instance segmentation

no code implementations7 Jun 2021 Kuikun Liu, Jie Yang, Cai Sun, Haoyuan Chi

Currently, instance segmentation is attracting more and more attention in machine learning region.

Binarization Instance Segmentation +2

Rotation Equivariant Feature Image Pyramid Network for Object Detection in Optical Remote Sensing Imagery

no code implementations2 Jun 2021 Pourya Shamsolmoali, Masoumeh Zareapoor, Jocelyn Chanussot, Huiyu Zhou, Jie Yang

The proposed model adopts single-shot detector in parallel with a lightweight image pyramid module to extract representative features and generate regions of interest in an optimization approach.

Object object-detection +1

A Novel Multi-scale Dilated 3D CNN for Epileptic Seizure Prediction

no code implementations5 May 2021 Ziyu Wang, Jie Yang, Mohamad Sawan

Accurate prediction of epileptic seizures allows patients to take preventive measures in advance to avoid possible injuries.

EEG Electroencephalogram (EEG) +2

UniGNN: a Unified Framework for Graph and Hypergraph Neural Networks

1 code implementation3 May 2021 Jing Huang, Jie Yang

In this paper, we propose UniGNN, a unified framework for interpreting the message passing process in graph and hypergraph neural networks, which can generalize general GNN models into hypergraphs.

Graph Representation Learning

Residual Enhanced Multi-Hypergraph Neural Network

1 code implementation2 May 2021 Jing Huang, Xiaolin Huang, Jie Yang

Hypergraphs are a generalized data structure of graphs to model higher-order correlations among entities, which have been successfully adopted into various research domains.

Representation Learning

Towards Unbiased Random Features with Lower Variance For Stationary Indefinite Kernels

1 code implementation13 Apr 2021 Qin Luo, Kun Fang, Jie Yang, Xiaolin Huang

Random Fourier Features (RFF) demonstrate wellappreciated performance in kernel approximation for largescale situations but restrict kernels to be stationary and positive definite.

regression

FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation

2 code implementations8 Mar 2021 Lingtong Kong, Chunhua Shen, Jie Yang

Experiments on both synthetic Sintel data and real-world KITTI datasets demonstrate the effectiveness of the proposed approach, which needs only 1/10 computation of comparable networks to achieve on par accuracy.

Optical Flow Estimation

Unsupervised Motion Representation Enhanced Network for Action Recognition

no code implementations5 Mar 2021 Xiaohang Yang, Lingtong Kong, Jie Yang

Learning reliable motion representation between consecutive frames, such as optical flow, has proven to have great promotion to video understanding.

Action Recognition Optical Flow Estimation +2

A New Neuromorphic Computing Approach for Epileptic Seizure Prediction

no code implementations25 Feb 2021 Fengshi Tian, Jie Yang, Shiqi Zhao, Mohamad Sawan

Motivated by the energy-efficient spiking neural networks (SNNs), a neuromorphic computing approach for seizure prediction is proposed in this work.

EEG Electroencephalogram (EEG) +2

Deep Deformation Detail Synthesis for Thin Shell Models

no code implementations23 Feb 2021 Lan Chen, Lin Gao, Jie Yang, Shibiao Xu, Juntao Ye, Xiaopeng Zhang, Yu-Kun Lai

Moreover, as such methods only add details, they require coarse meshes to be close to fine meshes, which can be either impossible, or require unrealistic constraints when generating fine meshes.

Mobile-end Tone Mapping based on Integral Image and Integral Histogram

no code implementations2 Feb 2021 Jie Yang, Mengchen Lin, Ziyi Liu, Ulian Shahnovich, Orly Yadid-Pecht

It is especially crucial for mobile devices because most of the images taken today are from mobile phones, hence such technology is highly demanded in the consumer market of mobile devices and is essential for a good customer experience.

Tone Mapping

Tone Mapping Based on Multi-scale Histogram Synthesis

1 code implementation31 Jan 2021 Jie Yang, Ziyi Liu, Ulian Shahnovich, Orly Yadid-Pecht

HVS perceives luminance differently when under different adaptation levels, and therefore our algorithm uses functions built upon different scales to tone map pixels to different values.

Tone Mapping

OAS-Net: Occlusion Aware Sampling Network for Accurate Optical Flow

no code implementations31 Jan 2021 Lingtong Kong, Xiaohang Yang, Jie Yang

Optical flow estimation is an essential step for many real-world computer vision tasks.

Optical Flow Estimation

Deep Reformulated Laplacian Tone Mapping

1 code implementation31 Jan 2021 Jie Yang, Ziyi Liu, Mengchen Lin, Svetlana Yanushkevich, Orly Yadid-Pecht

The reformulated Laplacian pyramid always decompose a WDR image into two frequency bands where the low-frequency band is global feature-oriented, and the high-frequency band is local feature-oriented.

Tone Mapping

A Survey on Extraction of Causal Relations from Natural Language Text

no code implementations16 Jan 2021 Jie Yang, Soyeon Caren Han, Josiah Poon

Existing causality extraction techniques include knowledge-based, statistical machine learning(ML)-based, and deep learning-based approaches.

BIG-bench Machine Learning Feature Engineering +2

Single Image 3D Shape Retrieval via Cross-Modal Instance and Category Contrastive Learning

no code implementations ICCV 2021 Ming-Xian Lin, Jie Yang, He Wang, Yu-Kun Lai, Rongfei Jia, Binqiang Zhao, Lin Gao

Inspired by the great success in recent contrastive learning works on self-supervised representation learning, we propose a novel IBSR pipeline leveraging contrastive learning.

3D Shape Retrieval Contrastive Learning +4

Image Synthesis with Adversarial Networks: a Comprehensive Survey and Case Studies

1 code implementation26 Dec 2020 Pourya Shamsolmoali, Masoumeh Zareapoor, Eric Granger, Huiyu Zhou, Ruili Wang, M. Emre Celebi, Jie Yang

However, there is a lack of comprehensive review in this field, especially lack of a collection of GANs loss-variant, evaluation metrics, remedies for diverse image generation, and stable training.

Image-to-Image Translation Translation

DFR: Deep Feature Reconstruction for Unsupervised Anomaly Segmentation

1 code implementation13 Dec 2020 Jie Yang, Yong Shi, Zhiquan Qi

Concretely, we develop a multi-scale regional feature generator that can generate multiple spatial context-aware representations from pre-trained deep convolutional networks for every subregion of an image.

Anomaly Detection Descriptive

Learning Tubule-Sensitive CNNs for Pulmonary Airway and Artery-Vein Segmentation in CT

1 code implementation10 Dec 2020 Yulei Qin, Hao Zheng, Yun Gu, Xiaolin Huang, Jie Yang, Lihui Wang, Feng Yao, Yue-Min Zhu, Guang-Zhong Yang

Training convolutional neural networks (CNNs) for segmentation of pulmonary airway, artery, and vein is challenging due to sparse supervisory signals caused by the severe class imbalance between tubular targets and background.

Anatomy Representation Learning +1

Multiscale Mesh Deformation Component Analysis with Attention-based Autoencoders

no code implementations4 Dec 2020 Jie Yang, Lin Gao, Qingyang Tan, Yihua Huang, Shihong Xia, Yu-Kun Lai

The attention mechanism is designed to learn to softly weight multi-scale deformation components in active deformation regions, and the stacked attention-based autoencoder is learned to represent the deformation components at different scales.

Unsupervised anomaly segmentation via deep feature reconstruction

1 code implementation26 Nov 2020 Jie Yang

Concretely, we develop a multi-scale regional feature generator that can generate multiple spatial context-aware representations from pre-trained deep convolutional networks for every subregion of an image.

Anomaly Detection Descriptive

Alleviating Class-wise Gradient Imbalance for Pulmonary Airway Segmentation

1 code implementation24 Nov 2020 Hao Zheng, Yulei Qin, Yun Gu, Fangfang Xie, Jie Yang, Jiayuan Sun, Guang-Zhong Yang

Due to the small size and scattered spatial distribution of peripheral bronchi, this is hampered by severe class imbalance between foreground and background regions, which makes it challenging for CNN-based methods to parse distal small airways.

Action Segmentation

Towards Robust Neural Networks via Orthogonal Diversity

2 code implementations23 Oct 2020 Kun Fang, Qinghua Tao, Yingwen Wu, Tao Li, Jia Cai, Feipeng Cai, Xiaolin Huang, Jie Yang

In this way, the proposed DIO augments the model and enhances the robustness of DNN itself as the learned features can be corrected by these mutually-orthogonal paths.

Adversarial Robustness Data Augmentation

One-shot Distributed Algorithm for Generalized Eigenvalue Problem

no code implementations22 Oct 2020 Kexin Lv, Fan He, Xiaolin Huang, Jie Yang, Liming Chen

Nowadays, more and more datasets are stored in a distributed way for the sake of memory storage or data privacy.

RISA-Net: Rotation-Invariant Structure-Aware Network for Fine-Grained 3D Shape Retrieval

1 code implementation2 Oct 2020 Rao Fu, Jie Yang, Jiawei Sun, Fang-Lue Zhang, Yu-Kun Lai, Lin Gao

Fine-grained 3D shape retrieval aims to retrieve 3D shapes similar to a query shape in a repository with models belonging to the same class, which requires shape descriptors to be capable of representing detailed geometric information to discriminate shapes with globally similar structures.

3D Object Retrieval 3D Shape Retrieval +1

Learn Robust Features via Orthogonal Multi-Path

no code implementations28 Sep 2020 Kun Fang, Xiaolin Huang, Yingwen Wu, Tao Li, Jie Yang

To defend adversarial attacks, we design a block containing multiple paths to learn robust features and the parameters of these paths are required to be orthogonal with each other.

Integrated Communication and Localization in mmWave Systems

no code implementations28 Sep 2020 Jie Yang, Jing Xu, Xiao Li, Shi Jin, Bo Gao

As the fifth-generation (5G) mobile communication system is being commercialized, extensive studies on the evolution of 5G and sixth-generation mobile communication systems have been conducted.

Multi-Level Graph Convolutional Network with Automatic Graph Learning for Hyperspectral Image Classification

no code implementations19 Sep 2020 Sheng Wan, Chen Gong, Shirui Pan, Jie Yang, Jian Yang

Nowadays, deep learning methods, especially the Graph Convolutional Network (GCN), have shown impressive performance in hyperspectral image (HSI) classification.

General Classification graph construction +2

End-to-end Kernel Learning via Generative Random Fourier Features

1 code implementation10 Sep 2020 Kun Fang, Fanghui Liu, Xiaolin Huang, Jie Yang

In the second-stage process, a linear learner is conducted with respect to the mapped random features.

Adversarial Robustness

Improving Language Generation with Sentence Coherence Objective

1 code implementation7 Sep 2020 Ruixiao Sun, Jie Yang, Mehrdad Yousefzadeh

Conditional story generation and contextual text continuation have become increasingly popular topics in NLP community.

Language Modelling Sentence +1

DSG-Net: Learning Disentangled Structure and Geometry for 3D Shape Generation

1 code implementation12 Aug 2020 Jie Yang, Kaichun Mo, Yu-Kun Lai, Leonidas J. Guibas, Lin Gao

While significant progress has been made, especially with recent deep generative models, it remains a challenge to synthesize high-quality shapes with rich geometric details and complex structure, in a controllable manner.

3D Shape Generation

Road Segmentation for Remote Sensing Images using Adversarial Spatial Pyramid Networks

1 code implementation10 Aug 2020 Pourya Shamsolmoali, Masoumeh Zareapoor, Huiyu Zhou, Ruili Wang, Jie Yang

We also propose a feature pyramid network that improves the performance of the proposed model by extracting effective features from all the layers of the network for describing different scales objects.

Domain Adaptation Image Generation +1

Oversampling Adversarial Network for Class-Imbalanced Fault Diagnosis

no code implementations7 Aug 2020 Masoumeh Zareapoor, Pourya Shamsolmoali, Jie Yang

In particular, we restore the balance in the imbalanced dataset by generating faulty samples from the proposed mixture of data distribution.

Fault Detection Generative Adversarial Network

Novel Subtypes of Pulmonary Emphysema Based on Spatially-Informed Lung Texture Learning

no code implementations9 Jul 2020 Jie Yang, Elsa D. Angelini, Pallavi P. Balte, Eric A. Hoffman, John H. M. Austin, Benjamin M. Smith, R. Graham Barr, Andrew F. Laine

Pulmonary emphysema overlaps considerably with chronic obstructive pulmonary disease (COPD), and is traditionally subcategorized into three subtypes previously identified on autopsy.

Computed Tomography (CT)

Analysis of Regularized Least Squares in Reproducing Kernel Krein Spaces

no code implementations1 Jun 2020 Fanghui Liu, Lei Shi, Xiaolin Huang, Jie Yang, Johan A. K. Suykens

In this paper, we study the asymptotic properties of regularized least squares with indefinite kernels in reproducing kernel Krein spaces (RKKS).

Hierarchical Feature Embedding for Attribute Recognition

no code implementations CVPR 2020 Jie Yang, Jiarou Fan, Yiru Wang, Yige Wang, Weihao Gan, Lin Liu, Wei Wu

Attribute recognition is a crucial but challenging task due to viewpoint changes, illumination variations and appearance diversities, etc.

Attribute

Adaptive Mixture Regression Network with Local Counting Map for Crowd Counting

1 code implementation ECCV 2020 Xiyang Liu, Jie Yang, Wenrui Ding

The crowd counting task aims at estimating the number of people located in an image or a frame from videos.

Crowd Counting regression

One-shot Distibuted Algorithm for PCA with RBF Kernels

1 code implementation6 May 2020 Fan He, Kexin Lv, Jie Yang, Xiaolin Huang

This letter proposes a one-shot algorithm for feature-distributed kernel PCA.

Clustering via torque balance with mass and distance

no code implementations27 Apr 2020 Jie Yang, Chin-Teng Lin

Grouping similar objects is a fundamental tool of scientific analysis, ubiquitous in disciplines from biology and chemistry to astronomy and pattern recognition.

Astronomy Clustering

Sparse Generalized Canonical Correlation Analysis: Distributed Alternating Iteration based Approach

no code implementations23 Apr 2020 Jia Cai, Kexin Lv, Junyi Huo, Xiaolin Huang, Jie Yang

To overcome this limitation, in this paper, we propose a sparse generalized canonical correlation analysis (GCCA), which could detect the latent relations of multiview data with sparse structures.

Imbalanced Data Learning by Minority Class Augmentation using Capsule Adversarial Networks

no code implementations5 Apr 2020 Pourya Shamsolmoali, Masoumeh Zareapoor, Linlin Shen, Abdul Hamid Sadka, Jie Yang

It improves learning from imbalanced data by incorporating the majority distribution structure in the generation of new minority samples.

Stereo Endoscopic Image Super-Resolution Using Disparity-Constrained Parallel Attention

no code implementations19 Mar 2020 Tianyi Zhang, Yun Gu, Xiaolin Huang, Enmei Tu, Jie Yang

In particular, we incorporate a disparity-based constraint mechanism into the generation of SR images in a deep neural network framework with an additional atrous parallax-attention modules.

Image Super-Resolution

AMIL: Adversarial Multi Instance Learning for Human Pose Estimation

1 code implementation18 Mar 2020 Pourya Shamsolmoali, Masoumeh Zareapoor, Huiyu Zhou, Jie Yang

The proposed adversarial residual multi-instance neural network that is based on pooling has been validated on two datasets for the human pose estimation task and successfully outperforms the other state-of-arts models.

Multiple Instance Learning Pose Estimation +2

A novel Deep Structure U-Net for Sea-Land Segmentation in Remote Sensing Images

no code implementations17 Mar 2020 Pourya Shamsolmoali, Masoumeh Zareapoor, Ruili Wang, Huiyu Zhou, Jie Yang

This paper presents a novel deep neural network structure for pixel-wise sea-land segmentation, a Residual Dense U-Net (RDU-Net), in complex and high-density remote sensing images.

Segmentation

Learning to Incorporate Structure Knowledge for Image Inpainting

1 code implementation11 Feb 2020 Jie Yang, Zhiquan Qi, Yong Shi

This paper develops a multi-task learning framework that attempts to incorporate the image structure knowledge to assist image inpainting, which is not well explored in previous works.

Image Inpainting Multi-Task Learning

Universal Adversarial Attack on Attention and the Resulting Dataset DAmageNet

no code implementations16 Jan 2020 Sizhe Chen, Zhengbao He, Chengjin Sun, Jie Yang, Xiaolin Huang

AoA enjoys a significant increase in transferability when the traditional cross entropy loss is replaced with the attention loss.

Adversarial Attack

Asymmetric Correlation Quantization Hashing for Cross-modal Retrieval

no code implementations14 Jan 2020 Lu Wang, Jie Yang

Due to the superiority in similarity computation and database storage for large-scale multiple modalities data, cross-modal hashing methods have attracted extensive attention in similarity retrieval across the heterogeneous modalities.

Cross-Modal Retrieval Quantization +1

Mixed-Precision Quantized Neural Network with Progressively Decreasing Bitwidth For Image Classification and Object Detection

no code implementations29 Dec 2019 Tianshu Chu, Qin Luo, Jie Yang, Xiaolin Huang

In addition, the results also demonstrate that the higher-precision bottom layers could boost the 1-bit network performance appreciably due to a better preservation of the original image information while the lower-precision posterior layers contribute to the regularization of $k-$bit networks.

General Classification Image Classification +3

CNN-Based Invertible Wavelet Scattering for the Investigation of Diffusion Properties of the In Vivo Human Heart in Diffusion Tensor Imaging

no code implementations17 Dec 2019 Zeyu Deng, Lihui Wang, Zixiang Kuai, Qijian Chen, Xinyu Cheng, Feng Yang, Jie Yang, Yue-Min Zhu

The results on both simulated and acquired in vivo cardiac DW images showed that the proposed WSCNN method effectively compensates for motion-induced signal loss and produces in vivo cardiac DW images with better quality and more coherent fiber structures with respect to existing methods, which makes it an interesting method for measuring correctly the diffusion properties of the in vivo human heart in DTI under free breathing.

Motion Compensation Translation

A Human-AI Loop Approach for Joint Keyword Discovery and Expectation Estimation in Micropost Event Detection

no code implementations2 Dec 2019 Akansha Bhardwaj, Jie Yang, Philippe Cudré-Mauroux

Such approaches are, however, limited as they fail to reliably estimate the informativeness of a keyword and its expectation for model training.

Event Detection Informativeness

Adaptive Initialization Method for K-means Algorithm

no code implementations27 Nov 2019 Jie Yang, Yu-Kai Wang, Xin Yao, Chin-Teng Lin

(c) The time complexity of the algorithm is quadratic, which is difficult to apply to large datasets.

Clustering

Random Fourier Features via Fast Surrogate Leverage Weighted Sampling

no code implementations20 Nov 2019 Fanghui Liu, Xiaolin Huang, Yudong Chen, Jie Yang, Johan A. K. Suykens

In this paper, we propose a fast surrogate leverage weighted sampling strategy to generate refined random Fourier features for kernel approximation.

Cluster-wise Unsupervised Hashing for Cross-Modal Similarity Search

no code implementations11 Nov 2019 Lu Wang, Jie Yang

Large-scale cross-modal hashing similarity retrieval has attracted more and more attention in modern search applications such as search engines and autopilot, showing great superiority in computation and storage.

Clustering Retrieval

Research Commentary on Recommendations with Side Information: A Survey and Research Directions

no code implementations19 Sep 2019 Zhu Sun, Qing Guo, Jie Yang, Hui Fang, Guibing Guo, Jie Zhang, Robin Burke

This Research Commentary aims to provide a comprehensive and systematic survey of the recent research on recommender systems with side information.

Knowledge Graphs Recommendation Systems +1

SDM-NET: Deep Generative Network for Structured Deformable Mesh

no code implementations13 Aug 2019 Lin Gao, Jie Yang, Tong Wu, Yu-Jie Yuan, Hongbo Fu, Yu-Kun Lai, Hao Zhang

At the structural level, we train a Structured Parts VAE (SP-VAE), which jointly learns the part structure of a shape collection and the part geometries, ensuring a coherence between global shape structure and surface details.

Mesh Variational Autoencoders with Edge Contraction Pooling

1 code implementation7 Aug 2019 Yu-Jie Yuan, Yu-Kun Lai, Jie Yang, Hongbo Fu, Lin Gao

3D shape analysis is an important research topic in computer vision and graphics.

A Generalized Framework for Edge-preserving and Structure-preserving Image Smoothing

1 code implementation23 Jul 2019 Wei Liu, Pingping Zhang, Yinjie Lei, Xiaolin Huang, Jie Yang, Ian Reid

In this paper, a non-convex non-smooth optimization framework is proposed to achieve diverse smoothing natures where even contradictive smoothing behaviors can be achieved.

image smoothing

Estimating brain age based on a healthy population with deep learning and structural MRI

no code implementations1 Jul 2019 Xinyang Feng, Zachary C. Lipton, Jie Yang, Scott A. Small, Frank A. Provenzano

Numerous studies have established that estimated brain age, as derived from statistical models trained on healthy populations, constitutes a valuable biomarker that is predictive of cognitive decline and various neurological diseases.

Age Estimation

A Review of Semi Supervised Learning Theories and Recent Advances

no code implementations28 May 2019 Enmei Tu, Jie Yang

Semi-supervised learning, which has emerged from the beginning of this century, is a new type of learning method between traditional supervised learning and unsupervised learning.

An Effective Two-Branch Model-Based Deep Network for Single Image Deraining

no code implementations14 May 2019 Yinglong Wang, Dong Gong, Jie Yang, Qinfeng Shi, Anton Van Den Hengel, Dehua Xie, Bing Zeng

Removing rain effects from an image is of importance for various applications such as autonomous driving, drone piloting, and photo editing.

Autonomous Driving Single Image Deraining

Robust Visual Tracking Revisited: From Correlation Filter to Template Matching

no code implementations15 Apr 2019 Fanghui Liu, Chen Gong, Xiaolin Huang, Tao Zhou, Jie Yang, DaCheng Tao

In this paper, we propose a novel matching based tracker by investigating the relationship between template matching and the recent popular correlation filter based trackers (CFTs).

Template Matching Visual Tracking

A Regularization Approach for Instance-Based Superset Label Learning

no code implementations5 Apr 2019 Chen Gong, Tongliang Liu, Yuanyan Tang, Jian Yang, Jie Yang, DaCheng Tao

As a result, the intrinsic constraints among different candidate labels are deployed, and the disambiguated labels generated by RegISL are more discriminative and accurate than those output by existing instance-based algorithms.

Cannot find the paper you are looking for? You can Submit a new open access paper.