Search Results for author: Chi Zhang

Found 221 papers, 75 papers with code

Edge-based Parametric Digital Twins for Intelligent Building Indoor Climate Modeling

no code implementations7 Mar 2024 Zhongjun Ni, Chi Zhang, Magnus Karlsson, Shaofang Gong

Digital transformation in the built environment generates vast data for developing data-driven models to optimize building operations.

Edge-computing Time Series

MovieLLM: Enhancing Long Video Understanding with AI-Generated Movies

no code implementations3 Mar 2024 Zhende Song, Chenchen Wang, Jiamu Sheng, Chi Zhang, Gang Yu, Jiayuan Fan, Tao Chen

The development of multimodal models has marked a significant step forward in how machines understand videos.

Video Understanding

Neural Networks with (Low-Precision) Polynomial Approximations: New Insights and Techniques for Accuracy Improvement

no code implementations17 Feb 2024 Chi Zhang, Man Ho Au, Siu Ming Yiu

Experiments showed that combination of our solutions is very effective: at the same precision, our PANN is 10% to 50% more accurate than state-of-the-arts; and at the same accuracy, our PANN only requires a precision of $2^{-9}$ while state-of-the-art solution requires a precision of $2^{-12}$ using the ResNet-20 model on CIFAR-10 dataset.

Privacy Preserving

CounterCLR: Counterfactual Contrastive Learning with Non-random Missing Data in Recommendation

no code implementations8 Feb 2024 Jun Wang, Haoxuan Li, Chi Zhang, Dongxu Liang, Enyun Yu, Wenwu Ou, Wenjia Wang

Recommender systems are designed to learn user preferences from observed feedback and comprise many fundamental tasks, such as rating prediction and post-click conversion rate (pCVR) prediction.

Contrastive Learning counterfactual +3

Ray Denoising: Depth-aware Hard Negative Sampling for Multi-view 3D Object Detection

2 code implementations6 Feb 2024 Feng Liu, Tengteng Huang, Qianjing Zhang, Haotian Yao, Chi Zhang, Fang Wan, Qixiang Ye, Yanzhao Zhou

Multi-view 3D object detection systems often struggle with generating precise predictions due to the challenges in estimating depth from images, increasing redundant and incorrect detections.

3D Object Detection Denoising +1

Integration of cognitive tasks into artificial general intelligence test for large models

no code implementations4 Feb 2024 Youzhi Qu, Chen Wei, Penghui Du, Wenxin Che, Chi Zhang, Wanli Ouyang, Yatao Bian, Feiyang Xu, Bin Hu, Kai Du, Haiyan Wu, Jia Liu, Quanying Liu

During the evolution of large models, performance evaluation is necessarily performed to assess their capabilities and ensure safety before practical application.

A Survey on Data-Centric Recommender Systems

no code implementations31 Jan 2024 Riwei Lai, Li Chen, Rui Chen, Chi Zhang

Recommender systems (RSs) have become an essential tool for mitigating information overload in a range of real-world applications.

Recommendation Systems

Stream Query Denoising for Vectorized HD Map Construction

no code implementations17 Jan 2024 Shuo Wang, Fan Jia, Yingfei Liu, Yucheng Zhao, Zehui Chen, Tiancai Wang, Chi Zhang, Xiangyu Zhang, Feng Zhao

This paper introduces the Stream Query Denoising (SQD) strategy as a novel approach for temporal modeling in high-definition map (HD-map) construction.

Autonomous Driving Denoising

Adaptive Hardness Negative Sampling for Collaborative Filtering

1 code implementation10 Jan 2024 Riwei Lai, Rui Chen, Qilong Han, Chi Zhang, Li Chen

Negative sampling is essential for implicit collaborative filtering to provide proper negative training signals so as to achieve desirable performance.

Collaborative Filtering

DreamGaussian4D: Generative 4D Gaussian Splatting

1 code implementation28 Dec 2023 Jiawei Ren, Liang Pan, Jiaxiang Tang, Chi Zhang, Ang Cao, Gang Zeng, Ziwei Liu

Remarkable progress has been made in 4D content generation recently.

AppAgent: Multimodal Agents as Smartphone Users

no code implementations21 Dec 2023 Chi Zhang, Zhao Yang, Jiaxuan Liu, Yucheng Han, Xin Chen, Zebiao Huang, Bin Fu, Gang Yu

Recent advancements in large language models (LLMs) have led to the creation of intelligent agents capable of performing complex tasks.

Navigate

Solving the swing-up and balance task for the Acrobot and Pendubot with SAC

no code implementations18 Dec 2023 Chi Zhang, Akhil Sathuluri, Markus Zimmermann

We present a solution of the swing-up and balance task for the pendubot and acrobot for the participation in the AI Olympics competition at IJCAI 2023.

Acrobot Position +2

M3DBench: Let's Instruct Large Models with Multi-modal 3D Prompts

1 code implementation17 Dec 2023 Mingsheng Li, Xin Chen, Chi Zhang, Sijin Chen, Hongyuan Zhu, Fukun Yin, Gang Yu, Tao Chen

Furthermore, we establish a new benchmark for assessing the performance of large models in understanding multi-modal 3D prompts.

Instruction Following

ICD-LM: Configuring Vision-Language In-Context Demonstrations by Language Modeling

1 code implementation15 Dec 2023 Yingzhe Peng, Xu Yang, Haoxuan Ma, Shuo Xu, Chi Zhang, Yucheng Han, Hanwang Zhang

Moreover, during data construction, we use the LVLM intended for ICL implementation to validate the strength of each ICD sequence, resulting in a model-specific dataset and the ICD-LM trained by this dataset is also model-specific.

Image Captioning In-Context Learning +4

Creative Agents: Empowering Agents with Imagination for Creative Tasks

1 code implementation5 Dec 2023 Chi Zhang, Penglin Cai, Yuhui Fu, Haoqi Yuan, Zongqing Lu

We benchmark creative tasks with the challenging open-world game Minecraft, where the agents are asked to create diverse buildings given free-form language instructions.

Instruction Following Language Modelling +1

FaceStudio: Put Your Face Everywhere in Seconds

no code implementations5 Dec 2023 Yuxuan Yan, Chi Zhang, Rui Wang, Yichao Zhou, Gege Zhang, Pei Cheng, Gang Yu, Bin Fu

This study investigates identity-preserving image synthesis, an intriguing task in image generation that seeks to maintain a subject's identity while adding a personalized, stylistic touch.

Image Generation

I-PHYRE: Interactive Physical Reasoning

no code implementations4 Dec 2023 Shiqian Li, Kewen Wu, Chi Zhang, Yixin Zhu

Current evaluation protocols predominantly assess physical reasoning in stationary scenes, creating a gap in evaluating agents' abilities to interact with dynamic events.

Zero-shot Generalization

LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning

1 code implementation30 Nov 2023 Sijin Chen, Xin Chen, Chi Zhang, Mingsheng Li, Gang Yu, Hao Fei, Hongyuan Zhu, Jiayuan Fan, Tao Chen

However, developing LMMs that can comprehend, reason, and plan in complex and diverse 3D environments remains a challenging topic, especially considering the demand for understanding permutation-invariant point cloud 3D representations of the 3D scene.

3D dense captioning Dense Captioning +1

ShapeGPT: 3D Shape Generation with A Unified Multi-modal Language Model

1 code implementation29 Nov 2023 Fukun Yin, Xin Chen, Chi Zhang, Biao Jiang, Zibo Zhao, Jiayuan Fan, Gang Yu, Taihao Li, Tao Chen

The advent of large language models, enabling flexibility through instruction-driven approaches, has revolutionized many traditional generative tasks, but large models for 3D data, particularly in comprehensively handling 3D shapes with other modalities, are still under-explored.

3D Shape Generation Language Modelling +1

Panacea: Panoramic and Controllable Video Generation for Autonomous Driving

no code implementations28 Nov 2023 Yuqing Wen, Yucheng Zhao, Yingfei Liu, Fan Jia, Yanhui Wang, Chong Luo, Chi Zhang, Tiancai Wang, Xiaoyan Sun, Xiangyu Zhang

This work notably propels the field of autonomous driving by effectively augmenting the training dataset used for advanced BEV perception techniques.

Autonomous Driving Video Generation

ChartLlama: A Multimodal LLM for Chart Understanding and Generation

no code implementations27 Nov 2023 Yucheng Han, Chi Zhang, Xin Chen, Xu Yang, Zhibin Wang, Gang Yu, Bin Fu, Hanwang Zhang

Next, we introduce ChartLlama, a multi-modal large language model that we've trained using our created dataset.

Language Modelling Large Language Model

ADriver-I: A General World Model for Autonomous Driving

no code implementations22 Nov 2023 Fan Jia, Weixin Mao, Yingfei Liu, Yucheng Zhao, Yuqing Wen, Chi Zhang, Xiangyu Zhang, Tiancai Wang

Based on the vision-action pairs, we construct a general world model based on MLLM and diffusion model for autonomous driving, termed ADriver-I.

Autonomous Driving

Transfer Attacks and Defenses for Large Language Models on Coding Tasks

no code implementations22 Nov 2023 Chi Zhang, Zifan Wang, Ravi Mangal, Matt Fredrikson, Limin Jia, Corina Pasareanu

They improve upon previous neural network models of code, such as code2seq or seq2seq, that already demonstrated competitive results when performing tasks such as code summarization and identifying code vulnerabilities.

Code Summarization

Self-Supervised 3D Scene Flow Estimation and Motion Prediction using Local Rigidity Prior

no code implementations17 Oct 2023 Ruibo Li, Chi Zhang, Zhe Wang, Chunhua Shen, Guosheng Lin

By rigidly aligning each region with its potential counterpart in the target point cloud, we obtain a region-specific rigid transformation to generate its pseudo flow labels.

Motion Estimation motion prediction +2

CrossZoom: Simultaneously Motion Deblurring and Event Super-Resolving

1 code implementation29 Sep 2023 Chi Zhang, Xiang Zhang, Mingyuan Lin, Cheng Li, Chu He, Wen Yang, Gui-Song Xia, Lei Yu

Even though the collaboration between traditional and neuromorphic event cameras brings prosperity to frame-event based vision applications, the performance is still confined by the resolution gap crossing two modalities in both spatial and temporal domains.

Deblurring Event-based vision

Robust Geometry-Preserving Depth Estimation Using Differentiable Rendering

no code implementations ICCV 2023 Chi Zhang, Wei Yin, Gang Yu, Zhibin Wang, Tao Chen, Bin Fu, Joey Tianyi Zhou, Chunhua Shen

In this paper, we propose a learning framework that trains models to predict geometry-preserving depth without requiring extra data or annotations.

Monocular Depth Estimation

Learning Parallax for Stereo Event-based Motion Deblurring

no code implementations18 Sep 2023 Mingyuan Lin, Chi Zhang, Chu He, Lei Yu

To tackle this problem, we propose a novel coarse-to-fine framework, named NETwork of Event-based motion Deblurring with STereo event and intensity cameras (St-EDNet), to recover high-quality images directly from the misaligned inputs, consisting of a single blurry image and the concurrent event streams.

Deblurring Stereo Matching

PivotNet: Vectorized Pivot Learning for End-to-end HD Map Construction

2 code implementations ICCV 2023 Wenjie Ding, Limeng Qiao, Xi Qiu, Chi Zhang

Furthermore, to supervise the position and topology of the vectorized point predictions, we propose a dynamic vectorized sequence loss.

Autonomous Driving

DPF-Net: Combining Explicit Shape Priors in Deformable Primitive Field for Unsupervised Structural Reconstruction of 3D Objects

no code implementations ICCV 2023 Qingyao Shuai, Chi Zhang, Kaizhi Yang, Xuejin Chen

Unsupervised methods for reconstructing structures face significant challenges in capturing the geometric details with consistent structures among diverse shapes of the same category.

IT3D: Improved Text-to-3D Generation with Explicit View Synthesis

1 code implementation22 Aug 2023 YiWen Chen, Chi Zhang, Xiaofeng Yang, Zhongang Cai, Gang Yu, Lei Yang, Guosheng Lin

Recent strides in Text-to-3D techniques have been propelled by distilling knowledge from powerful large text-to-image diffusion models (LDMs).

Text to 3D

X-VoE: Measuring eXplanatory Violation of Expectation in Physical Events

1 code implementation ICCV 2023 Bo Dai, Linge Wang, Baoxiong Jia, Zeyu Zhang, Song-Chun Zhu, Chi Zhang, Yixin Zhu

Intuitive physics is pivotal for human understanding of the physical world, enabling prediction and interpretation of events even in infancy.

Weakly supervised learning for pattern classification in serial femtosecond crystallography

no code implementations30 Jul 2023 Jianan Xie, Ji Liu, Chi Zhang, Xihui Chen, Ping Huai, Jie Zheng, Xiaofeng Zhang

Th is heavy dependence on labeled datasets will seriously restrict the application of networks, because it is very costly to annotate a large number of diffraction patterns.

Weakly-supervised Learning

ESSAformer: Efficient Transformer for Hyperspectral Image Super-resolution

1 code implementation ICCV 2023 Mingjin Zhang, Chi Zhang, Qiming Zhang, Jie Guo, Xinbo Gao, Jing Zhang

Single hyperspectral image super-resolution (single-HSI-SR) aims to restore a high-resolution hyperspectral image from a low-resolution observation.

Hyperspectral Image Super-Resolution Image Super-Resolution

A Phase-Coded Time-Domain Interleaved OTFS Waveform with Improved Ambiguity Function

no code implementations26 Jul 2023 Jiajun Zhu, Yanqun Tang, Chao Yang, Chi Zhang, Haoran Yin, Jiaojiao Xiong, Yuhua Chen

To enhance the sensing performance of the orthogonal time frequency space (OTFS) waveform, we propose a novel time-domain interleaved cyclic-shifted P4-coded OTFS (TICP4-OTFS) with improved ambiguity function.

Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image

1 code implementation ICCV 2023 Wei Yin, Chi Zhang, Hao Chen, Zhipeng Cai, Gang Yu, Kaixuan Wang, Xiaozhi Chen, Chunhua Shen

State-of-the-art (SOTA) monocular metric depth estimation methods can only handle a single camera model and are unable to perform mixed-data training due to the metric ambiguity.

Ranked #16 on Monocular Depth Estimation on NYU-Depth V2 (using extra training data)

Image Reconstruction Monocular Depth Estimation +1

Brain in a Vat: On Missing Pieces Towards Artificial General Intelligence in Large Language Models

no code implementations7 Jul 2023 Yuxi Ma, Chi Zhang, Song-Chun Zhu

In this perspective paper, we first comprehensively review existing evaluations of Large Language Models (LLMs) using both standardized tests and ability-oriented benchmarks.

Unity

Event Detection from Social Media Stream: Methods, Datasets and Opportunities

no code implementations28 Jun 2023 Quanzhi Li, Yang Chao, Dong Li, Yao Lu, Chi Zhang

Social media streams contain large and diverse amount of information, ranging from daily-life stories to the latest global and local events and news.

Event Detection

MachMap: End-to-End Vectorized Solution for Compact HD-Map Construction

2 code implementations17 Jun 2023 Limeng Qiao, Yongchao Zheng, Peng Zhang, Wenjie Ding, Xi Qiu, Xing Wei, Chi Zhang

This report introduces the 1st place winning solution for the Autonomous Driving Challenge 2023 - Online HD-map Construction.

Autonomous Driving

End-to-End Vectorized HD-map Construction with Piecewise Bezier Curve

1 code implementation CVPR 2023 Limeng Qiao, Wenjie Ding, Xi Qiu, Chi Zhang

Vectorized high-definition map (HD-map) construction, which focuses on the perception of centimeter-level environmental information, has attracted significant research interest in the autonomous driving community.

Autonomous Driving

MEWL: Few-shot multimodal word learning with referential uncertainty

1 code implementation1 Jun 2023 Guangyuan Jiang, Manjie Xu, Shiji Xin, Wei Liang, Yujia Peng, Chi Zhang, Yixin Zhu

To fill in this gap, we introduce the MachinE Word Learning (MEWL) benchmark to assess how machines learn word meaning in grounded visual scenes.

An Overview of Resource Allocation in Integrated Sensing and Communication

no code implementations15 May 2023 Jinming Du, Yanqun Tang, Xizhang Wei, Jiaojiao Xiong, Jiajun Zhu, Haoran Yin, Chi Zhang, Haibo Chen

Integrated sensing and communication (ISAC) is considered as a promising solution for improving spectrum efficiency and relieving wireless spectrum congestion.

Leveraging Deep Learning and Digital Twins to Improve Energy Performance of Buildings

no code implementations8 May 2023 Zhongjun Ni, Chi Zhang, Magnus Karlsson, Shaofang Gong

Digital transformation in buildings accumulates massive operational data, which calls for smart solutions to utilize these data to improve energy performance.

You Only Need Two Detectors to Achieve Multi-Modal 3D Multi-Object Tracking

1 code implementation18 Apr 2023 Xiyang Wang, Chunyun Fu, JiaWei He, Mingguang Huang, Ting Meng, Siyu Zhang, Hangning Zhou, Ziyao Xu, Chi Zhang

In the classical tracking-by-detection (TBD) paradigm, detection and tracking are separately and sequentially conducted, and data association must be properly performed to achieve satisfactory tracking performance.

3D Multi-Object Tracking Object +3

Cross or Wait? Predicting Pedestrian Interaction Outcomes at Unsignalized Crossings

no code implementations17 Apr 2023 Chi Zhang, Amir Hossein Kalantari, Yue Yang, Zhongjun Ni, Gustav Markkula, Natasha Merat, Christian Berger

Predicting pedestrian behavior when interacting with vehicles is one of the most critical challenges in the field of automated driving.

Model Selection regression

Model-Agnostic Reachability Analysis on Deep Neural Networks

no code implementations3 Apr 2023 Chi Zhang, Wenjie Ruan, Fu Wang, Peipei Xu, Geyong Min, Xiaowei Huang

Verification plays an essential role in the formal analysis of safety-critical systems.

Skill Reinforcement Learning and Planning for Open-World Long-Horizon Tasks

no code implementations29 Mar 2023 Haoqi Yuan, Chi Zhang, Hongcheng Wang, Feiyang Xie, Penglin Cai, Hao Dong, Zongqing Lu

Our method outperforms baselines by a large margin and is the most sample-efficient demonstration-free RL method to solve Minecraft Tech Tree tasks.

Multi-Task Learning reinforcement-learning +1

Cyclic Delay-Doppler Shift: A Simple Transmit Diversity Technique for Delay-Doppler Waveforms in Doubly Selective Channels

no code implementations22 Feb 2023 Haoran Yin, Jiaojiao Xiong, Yu Zhou, Chi Zhang, Di Zhang, Xizhang Wei, Yanqun Tang

Delay-Doppler waveform design has been considered as a promising solution to achieve reliable communication under high-mobility channels for the space-air-ground-integrated networks (SAGIN).

Denoising and Prompt-Tuning for Multi-Behavior Recommendation

1 code implementation12 Feb 2023 Chi Zhang, Rui Chen, Xiangyu Zhao, Qilong Han, Li Li

In practical recommendation scenarios, users often interact with items under multi-typed behaviors (e. g., click, add-to-cart, and purchase).

Collaborative Filtering Denoising

Two-Stage Constrained Actor-Critic for Short Video Recommendation

1 code implementation3 Feb 2023 Qingpeng Cai, Zhenghai Xue, Chi Zhang, Wanqi Xue, Shuchang Liu, Ruohan Zhan, Xueliang Wang, Tianyou Zuo, Wentao Xie, Dong Zheng, Peng Jiang, Kun Gai

One the one hand, the platforms aims at optimizing the users' cumulative watch time (main goal) in long term, which can be effectively optimized by Reinforcement Learning.

Recommendation Systems reinforcement-learning +2

Reachability Analysis of Neural Network Control Systems

1 code implementation28 Jan 2023 Chi Zhang, Wenjie Ruan, Peipei Xu

We then reveal the working principles of applying Lipschitzian optimisation on NNCS verification and illustrate it by verifying an adaptive cruise control model.

Rolling Shutter Correction

Constrained Policy Optimization with Explicit Behavior Density for Offline Reinforcement Learning

1 code implementation NeurIPS 2023 Jing Zhang, Chi Zhang, Wenjia Wang, Bing-Yi Jing

Due to the inability to interact with the environment, offline reinforcement learning (RL) methods face the challenge of estimating the Out-of-Distribution (OOD) points.

reinforcement-learning Reinforcement Learning (RL)

Computationally Efficient 3D MRI Reconstruction with Adaptive MLP

no code implementations21 Jan 2023 Eric Z. Chen, Chi Zhang, Xiao Chen, Yikang Liu, Terrence Chen, Shanhui Sun

Recon3DMLP improves HR 3D reconstruction and outperforms several existing CNN-based models under similar GPU memory consumption, which demonstrates that Recon3DMLP is a practical solution for HR 3D MRI reconstruction.

3D Reconstruction MRI Reconstruction

Label-Guided Knowledge Distillation for Continual Semantic Segmentation on 2D Images and 3D Point Clouds

1 code implementation ICCV 2023 Ze Yang, Ruibo Li, Evan Ling, Chi Zhang, Yiming Wang, Dezhao Huang, Keng Teck Ma, Minhoe Hur, Guosheng Lin

To address this issue, we propose a new label-guided knowledge distillation (LGKD) loss, where the old model output is expanded and transplanted (with the guidance of the ground truth label) to form a semantically appropriate class correspondence with the new model output.

Continual Semantic Segmentation Knowledge Distillation +1

Discrepant and Multi-Instance Proxies for Unsupervised Person Re-Identification

no code implementations ICCV 2023 Chang Zou, Zeqi Chen, Zhichao Cui, Yuehu Liu, Chi Zhang

To completely and accurately represent the information contained in a cluster and learn discriminative features, we propose to maintain discrepant cluster proxies and multi-instance proxies for a cluster.

Contrastive Learning Unsupervised Person Re-Identification

BEAR: Physics-Principled Building Environment for Control and Reinforcement Learning

1 code implementation27 Nov 2022 Chi Zhang, Yuanyuan Shi, Yize Chen

Recent advancements in reinforcement learning algorithms have opened doors for researchers to operate and optimize building energy management systems autonomously.

energy management Management +3

Semantics-Preserving Sketch Embedding for Face Generation

no code implementations23 Nov 2022 Binxin Yang, Xuejin Chen, Chaoqun Wang, Chi Zhang, Zihan Chen, Xiaoyan Sun

With a semantic feature matching loss for effective semantic supervision, our sketch embedding precisely conveys the semantics in the input sketches to the synthesized images.

Face Generation Image-to-Image Translation

Dual Clustering Co-teaching with Consistent Sample Mining for Unsupervised Person Re-Identification

no code implementations7 Oct 2022 Zeqi Chen, Zhichao Cui, Chi Zhang, Jiahuan Zhou, Yuehu Liu

However, training two networks with a set of noisy pseudo labels reduces the complementarity of the two networks and results in label noise accumulation.

Clustering Pseudo Label +1

On the Learning Mechanisms in Physical Reasoning

no code implementations5 Oct 2022 Shiqian Li, Kewen Wu, Chi Zhang, Yixin Zhu

Taken together, the results on the challenging benchmark of PHYRE show that LfI is, if not better, as good as LfD for dynamics prediction.

Infrared: A Meta Bug Detector

no code implementations18 Sep 2022 Chi Zhang, Yu Wang, Linzhang Wang

The recent breakthroughs in deep learning methods have sparked a wave of interest in learning-based bug detectors.

Anomaly Detection

MRF-PINN: A Multi-Receptive-Field convolutional physics-informed neural network for solving partial differential equations

no code implementations6 Sep 2022 Shihong Zhang, Chi Zhang, Bosen Wang

To fill the gaps above, we propose three initiatives in this paper: (1) A Multi-Receptive-Field PINN (MRF-PINN) model is established to solve different types of PDEs on various mesh resolutions without manual tuning; (2) The dimensional balance method is used to estimate the loss weights when solving Navier-Stokes equations; (3) The Taylor polynomial is used to pad the virtual nodes near the boundaries for implementing high-order finite difference.

CRCNet: Few-shot Segmentation with Cross-Reference and Region-Global Conditional Networks

no code implementations23 Aug 2022 Weide Liu, Chi Zhang, Guosheng Lin, Fayao Liu

Few-shot segmentation aims to learn a segmentation model that can be generalized to novel classes with only a few training images.

Segmentation

KD-MVS: Knowledge Distillation Based Self-supervised Learning for Multi-view Stereo

1 code implementation21 Jul 2022 Yikang Ding, Qingtian Zhu, Xiangyue Liu, Wentao Yuan, Haotian Zhang, Chi Zhang

Supervised multi-view stereo (MVS) methods have achieved remarkable progress in terms of reconstruction quality, but suffer from the challenge of collecting large-scale ground-truth depth.

Knowledge Distillation Self-Supervised Learning

Sobolev Training for Implicit Neural Representations with Approximated Image Derivatives

1 code implementation21 Jul 2022 Wentao Yuan, Qingtian Zhu, Xiangyue Liu, Yikang Ding, Haotian Zhang, Chi Zhang

Recently, Implicit Neural Representations (INRs) parameterized by neural networks have emerged as a powerful and promising tool to represent different kinds of signals due to its continuous, differentiable properties, showing superiorities to classical discretized representations.

Inverse Rendering

Few-shot Open-set Recognition Using Background as Unknowns

no code implementations19 Jul 2022 Nan Song, Chi Zhang, Guosheng Lin

First, instead of learning the decision boundaries between seen classes, as is done in standard close-set classification, we reserve space for unseen classes, such that images located in these areas are recognized as the unseen classes.

Open Set Learning

A Synergistic Compilation Workflow for Tackling Crosstalk in Quantum Machines

no code implementations12 Jul 2022 Fei Hua, Yuwei Jin, Ang Li, Chenxu Liu, Meng Wang, Yanhao Chen, Chi Zhang, Ari Hayes, Samuel Stein, Minghao Guo, Yipeng Huang, Eddy Z. Zhang

Evaluations through simulation and on real IBM-Q devices show that our framework can significantly reduce the error rate by up to 6$\times$, with only $\sim$60\% circuit depth compared to state-of-the-art gate scheduling approaches.

Scheduling

Automatic Generation of Product-Image Sequence in E-commerce

1 code implementation26 Jun 2022 Xiaochuan Fan, Chi Zhang, Yong Yang, Yue Shang, Xueying Zhang, Zhen He, Yun Xiao, Bo Long, Lingfei Wu

For a platform with billions of products, it is extremely time-costly and labor-expensive to manually pick and organize qualified images.

DETR++: Taming Your Multi-Scale Detection Transformer

no code implementations7 Jun 2022 Chi Zhang, Lijuan Liu, Xiaoxue Zang, Frederick Liu, Hao Zhang, Xinying Song, Jindong Chen

Convolutional Neural Networks (CNN) have dominated the field of detection ever since the success of AlexNet in ImageNet classification [12].

object-detection Small Object Detection

On the Perils of Cascading Robust Classifiers

1 code implementation1 Jun 2022 Ravi Mangal, Zifan Wang, Chi Zhang, Klas Leino, Corina Pasareanu, Matt Fredrikson

We present \emph{cascade attack} (CasA), an adversarial attack against cascading ensembles, and show that: (1) there exists an adversarial input for up to 88\% of the samples where the ensemble claims to be certifiably robust and accurate; and (2) the accuracy of a cascading ensemble under our attack is as low as 11\% when it claims to be certifiably robust and accurate on 97\% of the test set.

Adversarial Attack

Multi-agent Databases via Independent Learning

no code implementations28 May 2022 Chi Zhang, Olga Papaemmanouil, Josiah P. Hanna, Aditya Akella

Thus, the paper attempts to address the question "Is it possible to design a database consisting of various learned components that cooperatively work to improve end-to-end query latency?".

Multi-agent Reinforcement Learning Scheduling

Constrained Reinforcement Learning for Short Video Recommendation

no code implementations26 May 2022 Qingpeng Cai, Ruohan Zhan, Chi Zhang, Jie Zheng, Guangwei Ding, Pinghua Gong, Dong Zheng, Peng Jiang

In this paper, we formulate the problem of short video recommendation as a constrained Markov Decision Process (MDP), where platforms want to optimize the main goal of user watch time in long term, with the constraint of accommodating the auxiliary responses of user interactions such as sharing/downloading videos.

Recommendation Systems reinforcement-learning +1

Scenario-based Multi-product Advertising Copywriting Generation for E-Commerce

no code implementations21 May 2022 Xueying Zhang, Kai Shen, Chi Zhang, Xiaochuan Fan, Yun Xiao, Zhen He, Bo Long, Lingfei Wu

In this paper, we proposed an automatic Scenario-based Multi-product Advertising Copywriting Generation system (SMPACG) for E-Commerce, which has been deployed on a leading Chinese e-commerce platform.

Attribute Language Modelling

Correction of out-of-focus microscopic images by deep learning

1 code implementation Computational and Structural Biotechnology Journal 2022 Chi Zhang, Hao Jiang, Weihuang Liu, Junyi Li, Shiming Tang, Mario Juhas, Yang Zhang.

Results To solve the out-of-focus issue in microscopy, we developed a Cycle Generative Adversarial Network (CycleGAN) based model and a multi-component weighted loss function.

Generative Adversarial Network Image Deblurring +1

Efficient Few-Shot Object Detection via Knowledge Inheritance

1 code implementation23 Mar 2022 Ze Yang, Chi Zhang, Ruibo Li, Yi Xu, Guosheng Lin

Upon this baseline, we devise an initializer named knowledge inheritance (KI) to reliably initialize the novel weights for the box classifier, which effectively facilitates the knowledge transfer process and boosts the adaptation speed.

Few-Shot Object Detection Object +2

Learning the Pedestrian-Vehicle Interaction for Pedestrian Trajectory Prediction

no code implementations10 Feb 2022 Chi Zhang, Christian Berger

In this paper, we study the interaction between pedestrians and vehicles and propose a novel neural network structure called the Pedestrian-Vehicle Interaction (PVI) extractor for learning the pedestrian-vehicle interaction.

Pedestrian Trajectory Prediction Trajectory Prediction

Multi-Centroid Representation Network for Domain Adaptive Person Re-ID

no code implementations22 Dec 2021 Yuhang Wu, Tengteng Huang, Haotian Yao, Chi Zhang, Yuanjie Shao, Chuchu Han, Changxin Gao, Nong Sang

First, we present a Domain-Specific Contrastive Learning (DSCL) mechanism to fully explore intradomain information by comparing samples only from the same domain.

Contrastive Learning Domain Adaptive Person Re-Identification +2

DSGPT: Domain-Specific Generative Pre-Training of Transformers for Text Generation in E-commerce Title and Review Summarization

no code implementations SIGIR 2021 Xueying Zhang, Yunjiang Jiang, Yue Shang, Zhaomeng Cheng, Chi Zhang, Xiaochuan Fan, Yun Xiao, Bo Long

We propose a novel domain-specific generative pre-training (DS-GPT) method for text generation and apply it to the product titleand review summarization problems on E-commerce mobile display. First, we adopt a decoder-only transformer architecture, which fitswell for fine-tuning tasks by combining input and output all to-gether.

Text Generation

Learning Algebraic Representation for Systematic Generalization in Abstract Reasoning

no code implementations25 Nov 2021 Chi Zhang, Sirui Xie, Baoxiong Jia, Ying Nian Wu, Song-Chun Zhu, Yixin Zhu

Extensive experiments show that by incorporating an algebraic treatment, the ALANS learner outperforms various pure connectionist models in domains requiring systematic generalization.

Abstract Algebra Systematic Generalization

Spatial Ensemble: a Novel Model Smoothing Mechanism for Student-Teacher Framework

1 code implementation NeurIPS 2021 Tengteng Huang, Yifan Sun, Xun Wang, Haotian Yao, Chi Zhang

Model smoothing is of central importance for obtaining a reliable teacher model in the student-teacher framework, where the teacher generates surrogate supervision signals to train the student.

Unity

Parallel Actors and Learners: A Framework for Generating Scalable RL Implementations

no code implementations3 Oct 2021 Chi Zhang, Sanmukh Rao Kuppannagari, Viktor K Prasanna

Current implementations exhibit poor performance due to challenges such as irregular memory accesses and thread-level synchronization overheads on CPU.

reinforcement-learning Reinforcement Learning (RL)

Degradation Attacks on Certifiably Robust Neural Networks

no code implementations29 Sep 2021 Klas Leino, Chi Zhang, Ravi Mangal, Matt Fredrikson, Bryan Parno, Corina Pasareanu

Certifiably robust neural networks employ provable run-time defenses against adversarial examples by checking if the model is locally robust at the input under evaluation.

valid

Adaptive Reliability Analysis for Multi-fidelity Models using a Collective Learning Strategy

no code implementations21 Sep 2021 Chi Zhang, Chaolin Song, Abdollah Shafieezadeh

In this context, CLF provides a new direction for quantifying the impact of new training points and can be easily extended with new learning functions to adapt to different reliability problems.

Meta Navigator: Search for a Good Adaptation Policy for Few-shot Learning

no code implementations ICCV 2021 Chi Zhang, Henghui Ding, Guosheng Lin, Ruibo Li, Changhu Wang, Chunhua Shen

Inspired by the recent success in Automated Machine Learning literature (AutoML), in this paper, we present Meta Navigator, a framework that attempts to solve the aforementioned limitation in few-shot learning by seeking a higher-level strategy and proffer to automate the selection from various few-shot learning designs.

AutoML Few-Shot Learning

GeneAnnotator: A Semi-automatic Annotation Tool for Visual Scene Graph

1 code implementation6 Sep 2021 Zhixuan Zhang, Chi Zhang, Zhenning Niu, Le Wang, Yuehu Liu

In this manuscript, we introduce a semi-automatic scene graph annotation tool for images, the GeneAnnotator.

Graph Generation Graph Learning +3

Scalable Data Annotation Pipeline for High-Quality Large Speech Datasets Development

1 code implementation1 Sep 2021 Mingkuan Liu, Chi Zhang, Hua Xing, Chao Feng, Monchu Chen, Judith Bishop, Grace Ngapo

Our A/B testing and pilot results demonstrated the HITL pipeline can improve annotation speed and capacity by at least 80% and quality is comparable to or higher than manual double pass annotation.

Vocal Bursts Intensity Prediction

Spatially and Robustly Hybrid Mixture Regression Model for Inference of Spatial Dependence

1 code implementation1 Sep 2021 Wennan Chang, Pengtao Dang, Changlin Wan, Xiaoyu Lu, Yue Fang, Tong Zhao, Yong Zang, Bo Li, Chi Zhang, Sha Cao

Compared with existing spatial regression models, our proposed model assumes the existence a few distinct regression models that are estimated based on observations that exhibit similar response-predictor relationships.

regression

Calibrating Class Activation Maps for Long-Tailed Visual Recognition

no code implementations29 Aug 2021 Chi Zhang, Guosheng Lin, Lvlong Lai, Henghui Ding, Qingyao Wu

First, we present a Class Activation Map Calibration (CAMC) module to improve the learning and prediction of network classifiers, by enforcing network prediction based on important image regions.

Representation Learning

Binocular Mutual Learning for Improving Few-shot Classification

1 code implementation ICCV 2021 Ziqi Zhou, Xi Qiu, Jiangtao Xie, Jianan Wu, Chi Zhang

From the perspective of class space on base set, existing methods either focus on utilizing all classes under a global view by normal pretraining, or pay more attention to adopt an episodic manner to train meta-tasks within few classes in a local view.

Classification Decision Making +1

DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection

1 code implementation ICCV 2021 Limeng Qiao, Yuxuan Zhao, Zhiyuan Li, Xi Qiu, Jianan Wu, Chi Zhang

Few-shot object detection, which aims at detecting novel objects rapidly from extremely few annotated examples of previously unseen classes, has attracted significant research interest in the community.

Classification Few-Shot Object Detection +1

Few-shot Segmentation with Optimal Transport Matching and Message Flow

no code implementations19 Aug 2021 Weide Liu, Chi Zhang, Henghui Ding, Tzu-Yi Hung, Guosheng Lin

In this work, we argue that every support pixel's information is desired to be transferred to all query pixels and propose a Correspondence Matching Network (CMNet) with an Optimal Transport Matching module to mine out the correspondence between the query and support images.

Few-Shot Semantic Segmentation Multi-Task Learning +2

Unified Regularity Measures for Sample-wise Learning and Generalization

no code implementations9 Aug 2021 Chi Zhang, Xiaoning Ma, Yu Liu, Le Wang, Yuanqi SU, Yuehu Liu

Fundamental machine learning theory shows that different samples contribute unequally both in learning and testing processes.

Learning Theory Memorization

M2IOSR: Maximal Mutual Information Open Set Recognition

no code implementations5 Aug 2021 Xin Sun, Henghui Ding, Chi Zhang, Guosheng Lin, Keck-Voon Ling

In this work, we aim to address the challenging task of open set recognition (OSR).

Open Set Learning

IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID

3 code implementations ICCV 2021 Yongxing Dai, Jun Liu, Yifan Sun, Zekun Tong, Chi Zhang, Ling-Yu Duan

To ensure these two properties to better characterize appropriate intermediate domains, we enforce the bridge losses on intermediate domains' prediction space and feature space, and enforce a diversity loss on the two domain factors.

Domain Adaptive Person Re-Identification Person Re-Identification

Principled Hyperedge Prediction with Structural Spectral Features and Neural Networks

no code implementations8 Jun 2021 Changlin Wan, Muhan Zhang, Wei Hao, Sha Cao, Pan Li, Chi Zhang

SNALS captures the joint interactions of a hyperedge by its local environment, which is retrieved by collecting the spectrum information of their connections.

Hyperedge Prediction

Social-IWSTCNN: A Social Interaction-Weighted Spatio-Temporal Convolutional Neural Network for Pedestrian Trajectory Prediction in Urban Traffic Scenarios

no code implementations26 May 2021 Chi Zhang, Christian Berger, Marco Dozza

In this paper, we use the recently released large-scale Waymo Open Dataset in urban traffic scenarios, which includes 374 urban training scenes and 76 urban testing scenes to analyze the performance of our proposed algorithm in comparison to the state-of-the-art (SOTA) models.

Pedestrian Trajectory Prediction Trajectory Prediction

More Separable and Easier to Segment: A Cluster Alignment Method for Cross-Domain Semantic Segmentation

no code implementations7 May 2021 Shuang Wang, Dong Zhao, Yi Li, Chi Zhang, Yuwei Guo, Qi Zang, Biao Hou, Licheng Jiao

Feature alignment between domains is one of the mainstream methods for Unsupervised Domain Adaptation (UDA) semantic segmentation.

Clustering Segmentation +2

Few-Shot Incremental Learning with Continually Evolved Classifiers

1 code implementation CVPR 2021 Chi Zhang, Nan Song, Guosheng Lin, Yun Zheng, Pan Pan, Yinghui Xu

First, we adopt a simple but effective decoupled learning strategy of representations and classifiers that only the classifiers are updated in each incremental session, which avoids knowledge forgetting in the representations.

Few-Shot Class-Incremental Learning Incremental Learning

Efficient DETR: Improving End-to-End Object Detector with Dense Prior

no code implementations3 Apr 2021 Zhuyu Yao, Jiangbo Ai, Boxun Li, Chi Zhang

By taking advantage of both dense detection and sparse set detection, Efficient DETR leverages dense prior to initialize the object containers and brings the gap of the 1-decoder structure and 6-decoder structure.

Object object-detection +1

ACRE: Abstract Causal REasoning Beyond Covariation

no code implementations CVPR 2021 Chi Zhang, Baoxiong Jia, Mark Edmonds, Song-Chun Zhu, Yixin Zhu

Causal induction, i. e., identifying unobservable mechanisms that lead to the observable relations among variables, has played a pivotal role in modern scientific discovery, especially in scenarios with only sparse and limited data.

Blocking Causal Discovery +1

Abstract Spatial-Temporal Reasoning via Probabilistic Abduction and Execution

no code implementations CVPR 2021 Chi Zhang, Baoxiong Jia, Song-Chun Zhu, Yixin Zhu

To fill in this gap, we propose a neuro-symbolic Probabilistic Abduction and Execution (PrAE) learner; central to the PrAE learner is the process of probabilistic abduction and execution on a probabilistic scene representation, akin to the mental manipulation of objects.

Attribute Logical Reasoning

Congestion-aware Multi-agent Trajectory Prediction for Collision Avoidance

1 code implementation26 Mar 2021 Xu Xie, Chi Zhang, Yixin Zhu, Ying Nian Wu, Song-Chun Zhu

Predicting agents' future trajectories plays a crucial role in modern AI systems, yet it is challenging due to intricate interactions exhibited in multi-agent systems, especially when it comes to collision avoidance.

Collision Avoidance Trajectory Prediction

Dynamic Metric Learning: Towards a Scalable Metric Space to Accommodate Multiple Semantic Scales

1 code implementation CVPR 2021 Yifan Sun, Yuke Zhu, Yuhan Zhang, Pengkun Zheng, Xi Qiu, Chi Zhang, Yichen Wei

%We argue that such flexibility is also important for deep metric learning, because different visual concepts indeed correspond to different semantic scales.

Metric Learning

Density-aware Haze Image Synthesis by Self-Supervised Content-Style Disentanglement

no code implementations11 Mar 2021 Chi Zhang, Zihang Lin, Liheng Xu, Zongliang Li, Wei Tang, Yuehu Liu, Gaofeng Meng, Le Wang, Li Li

The key procedure of haze image translation through adversarial training lies in the disentanglement between the feature only involved in haze synthesis, i. e. style feature, and the feature representing the invariant semantic content, i. e. content feature.

Disentanglement Image Generation +1

FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding

3 code implementations CVPR 2021 Bo Sun, Banghuai Li, Shengcai Cai, Ye Yuan, Chi Zhang

We present Few-Shot object detection via Contrastive proposals Encoding (FSCE), a simple yet effective approach to learning contrastive-aware object proposal encodings that facilitate the classification of detected objects.

Contrastive Learning Few-Shot Learning +4

On Instabilities of Conventional Multi-Coil MRI Reconstruction to Small Adverserial Perturbations

no code implementations25 Feb 2021 Chi Zhang, Jinghan Jia, Burhaneddin Yaman, Steen Moeller, Sijia Liu, Mingyi Hong, Mehmet Akçakaya

Although deep learning (DL) has received much attention in accelerated MRI, recent studies suggest small perturbations may lead to instabilities in DL-based reconstructions, leading to concern for their clinical application.

MRI Reconstruction

Nanoscale magnetization and current imaging using scanning-probe magneto-thermal microscopy

no code implementations4 Feb 2021 Chi Zhang, Jason M. Bartell, Jonathan C. Karsch, Isaiah Gray, Gregory D. Fuchs

In addition, we study the near-field and time-resolved characteristics of our signal and find that our instrument possesses a spatial resolution on the scale of 100 nm and a temporal resolution below 100 ps.

Mesoscale and Nanoscale Physics Materials Science

CycleSegNet: Object Co-segmentation with Cycle Refinement and Region Correspondence

no code implementations5 Jan 2021 Chi Zhang, Guankai Li, Guosheng Lin, Qingyao Wu, Rui Yao

Image co-segmentation is an active computer vision task that aims to segment the common objects from a set of images.

Segmentation

Learning Algebraic Representation for Abstract Spatial-Temporal Reasoning

no code implementations1 Jan 2021 Chi Zhang, Sirui Xie, Baoxiong Jia, Yixin Zhu, Ying Nian Wu, Song-Chun Zhu

We further show that the algebraic representation learned can be decoded by isomorphism and used to generate an answer.

Abstract Algebra Systematic Generalization

The Unreasonable Effectiveness of the Class-reversed Sampling in Tail Sample Memorization

no code implementations1 Jan 2021 Benyi Hu, Chi Zhang, Yuehu Liu, Le Wang, Li Liu

Long-tailed visual class recognition poses significant challenges to traditional machine learning and emerging deep networks due to its inherent class imbalance.

Memorization

RETHINKING LOCAL LOW RANK MATRIX DETECTION:A MULTIPLE-FILTER BASED NEURAL NETWORK FRAMEWORK

no code implementations1 Jan 2021 Pengtao Dang, Wennan Chang, Haiqi Zhu, Changlin Wan, Tong Zhao, Tingbo Guo, Paul Salama, Sha Cao, Chi Zhang

In this work, we first organize the general MLLRR problem into three subproblems based on different low rank properties , and we argue that most of existing efforts focus on only one category, which leaves the other two unsolved.

Recommendation Systems

BRAC+: Going Deeper with Behavior Regularized Offline Reinforcement Learning

no code implementations1 Jan 2021 Chi Zhang, Sanmukh Rao Kuppannagari, Viktor Prasanna

The goal of Offline Reinforcement Learning (RL) is to address this problem by learning effective policies using previously collected datasets.

Offline RL reinforcement-learning +1

Compositional Prototype Network with Multi-view Comparision for Few-Shot Point Cloud Semantic Segmentation

no code implementations28 Dec 2020 Xiaoyu Chen, Chi Zhang, Guosheng Lin, Jing Han

Moreover, when we use our network to handle the long-tail problem in a fully supervised point cloud segmentation dataset, it can also effectively boost the performance of the few-shot classes.

Few-Shot Learning Point Cloud Segmentation +2

Energy Efficient Federated Learning over Heterogeneous Mobile Devices via Joint Design of Weight Quantization and Wireless Transmission

no code implementations21 Dec 2020 Rui Chen, Liang Li, Kaiping Xue, Chi Zhang, Miao Pan, Yuguang Fang

To address these challenges, in this paper, we attempt to take FL into the design of future wireless networks and develop a novel joint design of wireless transmission and weight quantization for energy efficient FL over mobile devices.

Edge-computing Federated Learning +1

Exploring the many-body dynamics near a conical intersection with trapped Rydberg ions

no code implementations3 Dec 2020 Filippo Maria Gambetta, Chi Zhang, Markus Hennrich, Igor Lesanovsky, Weibin Li

Conical intersections between electronic potential energy surfaces are paradigmatic for the study of non-adiabatic processes in the excited states of large molecules.

Atomic Physics Quantum Physics

Manual-Label Free 3D Detection via An Open-Source Simulator

no code implementations16 Nov 2020 Zhen Yang, Chi Zhang, Huiming Guo, Zhaoxiang Zhang

In this paper, we propose a manual-label free 3D detection algorithm that leverages the CARLA simulator to generate a large amount of self-labeled training samples and introduces a novel Domain Adaptive VoxelNet (DA-VoxelNet) that can cross the distribution gap from the synthetic data to the real scenario.

Matched Queues with Matching Batch Pair (m, n)

no code implementations6 Sep 2020 Heng-Li Liu, Quan-Lin Li, Chi Zhang

In this paper, we discuss an interesting but challenging bilateral stochastically matching problem: A more general matched queue with matching batch pair (m, n) and two types (i. e., types A and B) of impatient customers, where the arrivals of A- and B-customers are both Poisson processes, m A-customers and n B-customers are matched as a group which leaves the system immediately, and the customers' impatient behavior is to guarantee the stability of the system.

Memory-based Jitter: Improving Visual Recognition on Long-tailed Data with Diversity In Memory

no code implementations22 Aug 2020 Jialun Liu, Jingwei Zhang, Yi Yang, Wenhui Li, Chi Zhang, Yifan Sun

With slight modifications, MBJ is applicable for two fundamental visual recognition tasks, \emph{i. e.}, deep image classification and deep metric learning (on long-tailed data).

Data Augmentation General Classification +4

Open Set Recognition with Conditional Probabilistic Generative Models

no code implementations12 Aug 2020 Xin Sun, Chi Zhang, Guosheng Lin, Keck-Voon Ling

A typical challenge that hinders their real-world applications is that unknown samples may be fed into the system during the testing phase, but traditional deep neural networks will wrongly recognize these unknown samples as one of the known classes.

Open Set Learning

Denoising individual bias for a fairer binary submatrix detection

1 code implementation31 Jul 2020 Changlin Wan, Wennan Chang, Tong Zhao, Sha Cao, Chi Zhang

Low rank representation of binary matrix is powerful in disentangling sparse individual-attribute associations, and has received wide applications.

Attribute Clustering +2

Geometric All-Way Boolean Tensor Decomposition

1 code implementation NeurIPS 2020 Changlin Wan, Wennan Chang, Tong Zhao, Sha Cao, Chi Zhang

Boolean tensor has been broadly utilized in representing high dimensional logical data collected on spatial, temporal and/or other relational domains.

Tensor Decomposition

Buffer Pool Aware Query Scheduling via Deep Reinforcement Learning

no code implementations21 Jul 2020 Chi Zhang, Ryan Marcus, Anat Kleiman, Olga Papaemmanouil

In this extended abstract, we propose a new technique for query scheduling with the explicit goal of reducing disk reads and thus implicitly increasing query performance.

reinforcement-learning Reinforcement Learning (RL) +1

Supervised clustering of high dimensional data using regularized mixture modeling

no code implementations19 Jul 2020 Wennan Chang, Changlin Wan, Yong Zang, Chi Zhang, Sha Cao

Identifying relationships between molecular variations and their clinical presentations has been challenged by the heterogeneous causes of a disease.

Clustering Computational Efficiency +1

Weight-dependent Gates for Network Pruning

no code implementations4 Jul 2020 Yun Li, Zechun Liu, Weiqun Wu, Haotian Yao, Xiangyu Zhang, Chi Zhang, Baoqun Yin

In this paper, a simple yet effective network pruning framework is proposed to simultaneously address the problems of pruning indicator, pruning ratio, and efficiency constraint.

Network Pruning

Learning Disentangled Representations of Video with Missing Data

1 code implementation23 Jun 2020 Armand Comas-Massagué, Chi Zhang, Zlatan Feric, Octavia Camps, Rose Yu

Missing data poses significant challenges while learning representations of video sequences.

Maximum Entropy Model Rollouts: Fast Model Based Policy Optimization without Compounding Errors

no code implementations8 Jun 2020 Chi Zhang, Sanmukh Rao Kuppannagari, Viktor K. Prasanna

Furthermore, we propose to generate \emph{diverse} model rollouts by non-uniform sampling of the environment states such that the entropy of the model rollouts is maximized.

Model-based Reinforcement Learning reinforcement-learning +1

Component-wise Adaptive Trimming For Robust Mixture Regression

no code implementations23 May 2020 Wennan Chang, Xinyu Zhou, Yong Zang, Chi Zhang, Sha Cao

Existing robust mixture regression methods suffer from outliers as they either conduct parameter estimation in the presence of outliers, or rely on prior knowledge of the level of outlier contamination.

Outlier Detection regression

Machine Number Sense: A Dataset of Visual Arithmetic Problems for Abstract and Relational Reasoning

2 code implementations25 Apr 2020 Wenhe Zhang, Chi Zhang, Yixin Zhu, Song-Chun Zhu

To endow such a crucial cognitive ability to machine intelligence, we propose a dataset, Machine Number Sense (MNS), consisting of visual arithmetic problems automatically generated using a grammar model--And-Or Graph (AOG).

Relational Reasoning Visual Reasoning

Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense

no code implementations20 Apr 2020 Yixin Zhu, Tao Gao, Lifeng Fan, Siyuan Huang, Mark Edmonds, Hangxin Liu, Feng Gao, Chi Zhang, Siyuan Qi, Ying Nian Wu, Joshua B. Tenenbaum, Song-Chun Zhu

We demonstrate the power of this perspective to develop cognitive AI systems with humanlike common sense by showing how to observe and apply FPICU with little training data to solve a wide range of challenging tasks, including tool use, planning, utility inference, and social learning.

Common Sense Reasoning Small Data Image Classification

Neural encoding and interpretation for high-level visual cortices based on fMRI using image caption features

no code implementations26 Mar 2020 Kai Qiao, Chi Zhang, Jian Chen, Linyuan Wang, Li Tong, Bin Yan

Except for deep network structure, the task or corresponding big dataset is also important for deep network models, but neglected by previous studies.

General Classification Image Classification

Conditional Gaussian Distribution Learning for Open Set Recognition

1 code implementation CVPR 2020 Xin Sun, Zhenning Yang, Chi Zhang, Guohao Peng, Keck-Voon Ling

A typical challenge is that unknown samples may be fed into the system during the testing phase and traditional deep neural networks will wrongly recognize the unknown sample as one of the known classes.

General Classification Open Set Learning

DeepEMD: Differentiable Earth Mover's Distance for Few-Shot Learning

5 code implementations15 Mar 2020 Chi Zhang, Yujun Cai, Guosheng Lin, Chunhua Shen

We employ the Earth Mover's Distance (EMD) as a metric to compute a structural distance between dense image representations to determine image relevance.

Classification Few-Shot Image Classification +4

BigGAN-based Bayesian reconstruction of natural images from human brain activity

no code implementations13 Mar 2020 Kai Qiao, Jian Chen, Linyuan Wang, Chi Zhang, Li Tong, Bin Yan

In this study, we proposed a new GAN-based Bayesian visual reconstruction method (GAN-BVRM) that includes a classifier to decode categories from fMRI data, a pre-trained conditional generator to generate natural images of specified categories, and a set of encoding models and evaluator to evaluate generated images.

Conditional Image Generation Generative Adversarial Network

Unsupervised Learning of Depth, Optical Flow and Pose with Occlusion from 3D Geometry

1 code implementation arXiv 2020 Guangming Wang, Chi Zhang, Hesheng Wang, Jingchuan Wang, Yong Wang, Xinlei Wang

In the occluded region, as depth and camera motion can provide more reliable motion estimation, they can be used to instruct unsupervised learning of optical flow.

Autonomous Driving Depth And Camera Motion +3

Cross-Spectrum Dual-Subspace Pairing for RGB-infrared Cross-Modality Person Re-Identification

no code implementations29 Feb 2020 Xing Fan, Hao Luo, Chi Zhang, Wei Jiang

Another challenge of RGB-infrared ReID is that the intra-person (images from the same person) discrepancy is often larger than the inter-person (images from different persons) discrepancy, so a dual-subspace pairing strategy is proposed to alleviate this problem.

Cross-Modality Person Re-identification Image Generation +1

Circle Loss: A Unified Perspective of Pair Similarity Optimization

11 code implementations CVPR 2020 Yifan Sun, Changmao Cheng, Yuhan Zhang, Chi Zhang, Liang Zheng, Zhongdao Wang, Yichen Wei

This paper provides a pair similarity optimization viewpoint on deep feature learning, aiming to maximize the within-class similarity $s_p$ and minimize the between-class similarity $s_n$.

 Ranked #1 on Face Verification on IJB-C (training dataset metric)

Face Recognition Face Verification +4

Collaborative Inference for Efficient Remote Monitoring

no code implementations12 Feb 2020 Chi Zhang, Yong Sheng Soh, Ling Feng, Tianyi Zhou, Qianxiao Li

While current machine learning models have impressive performance over a wide range of applications, their large size and complexity render them unsuitable for tasks such as remote monitoring on edge devices with limited storage and computational power.

Collaborative Inference

Learning Perceptual Inference by Contrasting

1 code implementation NeurIPS 2019 Chi Zhang, Baoxiong Jia, Feng Gao, Yixin Zhu, Hongjing Lu, Song-Chun Zhu

"Thinking in pictures," [1] i. e., spatial-temporal reasoning, effortless and instantaneous for humans, is believed to be a significant ability to perform logical induction and a crucial factor in the intellectual history of technology development.

Long-term planning, short-term adjustments

no code implementations25 Sep 2019 Hamed Khorasgani, Chi Zhang, Chetan Gupta, Susumu Serita

Our method can learn complex policies to achieve long-term goals and at the same time it can be easily adjusted to address short-term requirements without retraining.

Q-Learning Reinforcement Learning (RL)

EPOSIT: An Absolute Pose Estimation Method for Pinhole and Fish-Eye Cameras

1 code implementation19 Sep 2019 Zhaobing Kang, Wei Zou, Zheng Zhu, Chi Zhang, Hongxuan Ma

This paper presents a generic 6DOF camera pose estimation method, which can be used for both the pinhole camera and the fish-eye camera.

Pose Estimation

Re-ID Driven Localization Refinement for Person Search

no code implementations ICCV 2019 Chuchu Han, Jiacheng Ye, Yunshan Zhong, Xin Tan, Chi Zhang, Changxin Gao, Nong Sang

The state-of-the-art methods train the detector individually, and the detected bounding boxes may be sub-optimal for the following re-ID task.

Person Re-Identification Person Search

Determining the Scale of Impact from Denial-of-Service Attacks in Real Time Using Twitter

no code implementations12 Sep 2019 Chi Zhang, Bryan Wilkinson, Ashwinkumar Ganesan, Tim Oates

Another way to remove that limitation, an optional classification layer, trained on manually annotated DoS attack tweets, to filter out non-attack tweets can be used to increase precision at the expense of recall.

Fast And Efficient Boolean Matrix Factorization By Geometric Segmentation

no code implementations9 Sep 2019 Changlin Wan, Wennan Chang, Tong Zhao, Mengya Li, Sha Cao, Chi Zhang

Boolean matrix factorization (BMF) aims to find an approximation of a binary matrix as the Boolean product of two low rank Boolean matrices, which could generate vast amount of information for the patterns of relationships between the features and samples.

Computational Efficiency Denoising

Inverse Structural Design of Graphene/Boron Nitride Hybrids by Regressional GAN

1 code implementation21 Aug 2019 Yuan Dong, Dawei Li, Chi Zhang, Chuhan Wu, Hong Wang, Ming Xin, Jianlin Cheng, Jian Lin

A significant novelty of the proposed RGAN is that it combines the supervised and regressional convolutional neural network (CNN) with the traditional unsupervised GAN, thus overcoming the common technical barrier in the traditional GANs, which cannot generate data associated with given continuous quantitative labels.

Computational Physics Materials Science Applied Physics

Effective and efficient ROI-wise visual encoding using an end-to-end CNN regression model and selective optimization

1 code implementation27 Jul 2019 Kai Qiao, Chi Zhang, Jian Chen, Linyuan Wang, Li Tong, Bin Yan

Recently, visual encoding based on functional magnetic resonance imaging (fMRI) have realized many achievements with the rapid development of deep network computation.

regression

Distributed Optimization for Over-Parameterized Learning

no code implementations14 Jun 2019 Chi Zhang, Qianxiao Li

Moreover, we show that the more local updating can reduce the overall communication, even for an infinity number of steps where each node is free to update its local model to near-optimality before exchanging information.

Distributed Optimization

Bimodal Stereo: Joint Shape and Pose Estimation from Color-Depth Image Pair

no code implementations16 May 2019 Chi Zhang, Yuehu Liu, Ying Wu, Qilin Zhang, Le Wang

In the pipeline, the estimated shape is refined by the shape prior from the given depth map under the estimated pose.

Pose Estimation

Joint haze image synthesis and dehazing with mmd-vae losses

no code implementations15 May 2019 Zongliang Li, Chi Zhang, Gaofeng Meng, Yuehu Liu

Fog and haze are weathers with low visibility which are adversarial to the driving safety of intelligent vehicles equipped with optical sensors like cameras and LiDARs.

Autonomous Driving Image Dehazing +2

Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering

1 code implementation CVPR 2019 Chenyou Fan, Xiaofan Zhang, Shu Zhang, Wensheng Wang, Chi Zhang, Heng Huang

In this paper, we propose a novel end-to-end trainable Video Question Answering (VideoQA) framework with three major components: 1) a new heterogeneous memory which can effectively learn global context information from appearance and motion features; 2) a redesigned question memory which helps understand the complex semantics of question and highlights queried subjects; and 3) a new multimodal fusion layer which performs multi-step reasoning by attending to relevant visual and textual hints with self-updated attention.

Question Answering Video Question Answering +1

Re-Identification Supervised Texture Generation

no code implementations CVPR 2019 Jian Wang, Yunshan Zhong, Yachun Li, Chi Zhang, Yichen Wei

The estimation of 3D human body pose and shape from a single image has been extensively studied in recent years.

Person Re-Identification Texture Synthesis

Deep Learning Methods for Parallel Magnetic Resonance Image Reconstruction

no code implementations1 Apr 2019 Florian Knoll, Kerstin Hammernik, Chi Zhang, Steen Moeller, Thomas Pock, Daniel K. Sodickson, Mehmet Akcakaya

Both linear and non-linear methods are covered, followed by a discussion of recent efforts to further improve parallel imaging using machine learning, and specifically using artificial neural networks.

BIG-bench Machine Learning MRI Reconstruction

Perceive Where to Focus: Learning Visibility-aware Part-level Features for Partial Person Re-identification

1 code implementation CVPR 2019 Yifan Sun, Qin Xu, Ya-Li Li, Chi Zhang, Yikang Li, Shengjin Wang, Jian Sun

The visibility awareness allows VPM to extract region-level features and compare two images with focus on their shared regions (which are visible on both images).

Person Re-Identification

Category decoding of visual stimuli from human brain activity using a bidirectional recurrent neural network to simulate bidirectional information flows in human visual cortices

no code implementations19 Mar 2019 Kai Qiao, Jian Chen, Linyuan Wang, Chi Zhang, Lei Zeng, Li Tong, Bin Yan

Despite the hierarchically similar representations of deep network and human vision, visual information flows from primary visual cortices to high visual cortices and vice versa based on the bottom-up and top-down manners, respectively.

Neurons and Cognition

STNReID : Deep Convolutional Networks with Pairwise Spatial Transformer Networks for Partial Person Re-identification

no code implementations17 Mar 2019 Hao Luo, Xing Fan, Chi Zhang, Wei Jiang

Competition (or confrontation) is observed between the STN module and the ReID module, and two-stage training is applied to acquire a strong STNReID for partial ReID.

Person Re-Identification

RAVEN: A Dataset for Relational and Analogical Visual rEasoNing

no code implementations CVPR 2019 Chi Zhang, Feng Gao, Baoxiong Jia, Yixin Zhu, Song-Chun Zhu

In this work, we propose a new dataset, built in the context of Raven's Progressive Matrices (RPM) and aimed at lifting machine intelligence by associating vision with structural, relational, and analogical reasoning in a hierarchical representation.

Object Recognition Question Answering +2

A visual encoding model based on deep neural networks and transfer learning

no code implementations23 Feb 2019 Chi Zhang, Kai Qiao, Linyuan Wang, Li Tong, Guoen Hu, Ruyuan Zhang, Bin Yan

In this framework, we employ the transfer learning technique to incorporate a pre-trained DNN (i. e., AlexNet) and train a nonlinear mapping from visual features to brain activity.

Transfer Learning

A Top-down Approach to Articulated Human Pose Estimation and Tracking

no code implementations23 Jan 2019 Guanghan Ning, Ping Liu, Xiaochuan Fan, Chi Zhang

Both the tasks of multi-person human pose estimation and pose tracking in videos are quite challenging.

Pose Estimation Pose Tracking

Differentially Private ADMM for Distributed Medical Machine Learning

no code implementations7 Jan 2019 Jiahao Ding, Xiaoqi Qin, Wenjun Xu, Yanmin Gong, Chi Zhang, Miao Pan

Due to massive amounts of data distributed across multiple locations, distributed machine learning has attracted a lot of research interests.

BIG-bench Machine Learning

Dissociable neural representations of adversarially perturbed images in convolutional neural networks and the human brain

no code implementations22 Dec 2018 Chi Zhang, Xiaohan Duan, Linyuan Wang, Yongli Li, Bin Yan, Guoen Hu, Ruyuan Zhang, Li Tong

Furthermore, we show that voxel-encoding models trained on regular images can successfully generalize to the neural responses to AI images but not AN images.

Fast Botnet Detection From Streaming Logs Using Online Lanczos Method

no code implementations19 Dec 2018 Zheng Chen, Xinli Yu, Chi Zhang, Jin Zhang, Cui Lin, Bo Song, Jianliang Gao, Xiaohua Hu, Wei-Shih Yang, Erjia Yan

Botnet, a group of coordinated bots, is becoming the main platform of malicious Internet activities like DDOS, click fraud, web scraping, spam/rumor distribution, etc.

Two Birds with One Network: Unifying Failure Event Prediction and Time-to-failure Modeling

no code implementations18 Dec 2018 Karan Aggarwal, Onur Atan, Ahmed Farahat, Chi Zhang, Kosta Ristovski, Chetan Gupta

Classically, this problem has been posed in two different ways which are typically solved independently: (1) Remaining useful life (RUL) estimation as a long-term prediction task to estimate how much time is left in the useful life of the equipment and (2) Failure prediction (FP) as a short-term prediction task to assess the probability of a failure within a pre-specified time window.

Multi-Task Learning

MetaStyle: Three-Way Trade-Off Among Speed, Flexibility, and Quality in Neural Style Transfer

no code implementations13 Dec 2018 Chi Zhang, Yixin Zhu, Song-Chun Zhu

An unprecedented booming has been witnessed in the research area of artistic style transfer ever since Gatys et al. introduced the neural method.

Bilevel Optimization Style Transfer

SCPNet: Spatial-Channel Parallelism Network for Joint Holistic and Partial Person Re-Identification

no code implementations16 Oct 2018 Xing Fan, Hao Luo, Xuan Zhang, Lingxiao He, Chi Zhang, Wei Jiang

Holistic person re-identification (ReID) has received extensive study in the past few years and achieves impressive progress.

Person Re-Identification

Deep Learning Bandgaps of Topologically Doped Graphene

no code implementations28 Sep 2018 Yuan Dong, Chuhan Wu, Chi Zhang, Yingda Liu, Jianlin Cheng, Jian Lin

Moreover, given ubiquitous existence of topologies in materials, this work will stimulate widespread interests in applying deep learning algorithms to topological design of materials crossing atomic, nano-, meso-, and macro- scales.

Materials Science Computational Physics

Vector Learning for Cross Domain Representations

no code implementations27 Sep 2018 Shagan Sah, Chi Zhang, Thang Nguyen, Dheeraj Kumar Peri, Ameya Shringi, Raymond Ptucha

We leverage a sequence-to-sequence model to generate synthetic captions that have the same meaning for having a robust image generation.

Image Captioning Image Generation +2

Batch-normalized Recurrent Highway Networks

1 code implementation26 Sep 2018 Chi Zhang, Thang Nguyen, Shagan Sah, Raymond Ptucha, Alexander Loui, Carl Salvaggio

Gradient control plays an important role in feed-forward networks applied to various computer vision tasks.

Image Captioning

A Coarse-To-Fine Framework For Video Object Segmentation

no code implementations26 Sep 2018 Chi Zhang, Alexander Loui

In this study, we develop an unsupervised coarse-to-fine video analysis framework and prototype system to extract a salient object in a video sequence.

Object Segmentation +3

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