Search Results for author:
Found 40 papers, 12 papers with code
CML: A Contrastive Meta Learning Method to Estimate Human Label Confidence Scores and Reduce Data Collection Cost
In this paper, we propose a contrastive meta-learning framework (CML) to address the challenges introduced by noisy annotated data, specifically in the context of natural language processing.
基于有向异构图的发票明细税收分类方法(Tax Classification of Invoice Details Based on Directed Heterogeneous Graph)
税收是国家赖以生存的物质基础。为加快税收现代化, 方便纳税人便捷、规范开具增值税发票, 国税总局规定纳税人在税控系统开票前选择发票明细对应的税收分类才可正常开具发票。提高税收分类的准确度, 是构建税收风险指标和分析纳税人行为特征的重要基础。基于此, 本文提出了一种基于有向异构图的短文本分类模型(Heterogeneous Directed Graph Attenton Network, HDGAT), 利用发票明细间的有向信息建模, 引入外部知识, 显著地提高了发票明细的税收分类准确度。
GraphPub: Generation of Differential Privacy Graph with High Availability
In recent years, with the rapid development of graph neural networks (GNN), more and more graph datasets have been published for GNN tasks.
Efficient LLM Inference on CPUs
Large language models (LLMs) have demonstrated remarkable performance and tremendous potential across a wide range of tasks.
A Geometrical Approach to Evaluate the Adversarial Robustness of Deep Neural Networks
Hence, given different inputs, it requires different time for converging to an adversarial sample.
Compressing Context to Enhance Inference Efficiency of Large Language Models
This paper proposes a method called Selective Context that enhances the inference efficiency of LLMs by identifying and pruning redundancy in the input context to make the input more compact.
In the Blink of an Eye: Event-based Emotion Recognition
To the best of our knowledge, our method is the first eye-based emotion recognition method that leverages event-based cameras and spiking neural network.
A Unified Query-based Paradigm for Camouflaged Instance Segmentation
Due to the high similarity between camouflaged instances and the background, the recently proposed camouflaged instance segmentation (CIS) faces challenges in accurate localization and instance segmentation.
An Efficient Sparse Inference Software Accelerator for Transformer-based Language Models on CPUs
We apply our sparse accelerator on widely-used Transformer-based language models including Bert-Mini, DistilBERT, Bert-Base, and BERT-Large.
A Low-rank Matching Attention based Cross-modal Feature Fusion Method for Conversational Emotion Recognition
By setting a matching weight and calculating attention scores between modal features row by row, LMAM contains fewer parameters than the self-attention method.
APAM: Adaptive Pre-training and Adaptive Meta Learning in Language Model for Noisy Labels and Long-tailed Learning
Lastly, our sensitive analysis emphasizes the capability of the proposed framework to handle the long-tailed problem and mitigate the negative impact of noisy labels.
Head-Free Lightweight Semantic Segmentation with Linear Transformer
On the ADE20K dataset, our model achieves 41. 8 mIoU and 4. 6 GFLOPs, which is 4. 4 mIoU higher than Segformer, with 45% less GFLOPs.
Multi-view Spectral Polarization Propagation for Video Glass Segmentation
In this paper, we present the first polarization-guided video glass segmentation propagation solution (PGVS-Net) that can robustly and coherently propagate glass segmentation in RGB-P video sequences.
Single Depth-image 3D Reflection Symmetry and Shape Prediction
In this paper, we present Iterative Symmetry Completion Network (ISCNet), a single depth-image shape completion method that exploits reflective symmetry cues to obtain more detailed shapes.
PAI3D: Painting Adaptive Instance-Prior for 3D Object Detection
3D object detection is a critical task in autonomous driving.
Fast DistilBERT on CPUs
In this work, we propose a new pipeline for creating and running Fast Transformer models on CPUs, utilizing hardware-aware pruning, knowledge distillation, quantization, and our own Transformer inference runtime engine with optimized kernels for sparse and quantized operators.
ASD: Towards Attribute Spatial Decomposition for Prior-Free Facial Attribute Recognition
Representing the spatial properties of facial attributes is a vital challenge for facial attribute recognition (FAR).
Point Cloud Scene Completion with Joint Color and Semantic Estimation from Single RGB-D Image
Given a single RGB-D image, our method first predicts its semantic segmentation map and goes through the 3D volume branch to obtain a volumetric scene reconstruction as a guide to the next view inpainting step, which attempts to make up the missing information; the third step involves projecting the volume under the same view of the input, concatenating them to complete the current view RGB-D and segmentation map, and integrating all RGB-D and segmentation maps into the point cloud.
Spiking Transformers for Event-Based Single Object Tracking
In particular, the proposed architecture features a transformer module to provide global spatial information and a spiking neural network (SNN) module for extracting temporal cues.
Glass Segmentation Using Intensity and Spectral Polarization Cues
Transparent and semi-transparent materials pose significant challenges for existing scene understanding and segmentation algorithms due to their lack of RGB texture which impedes the extraction of meaningful features.
Ranked #14 on
Semantic Segmentation
on KITTI-360
Computationally Efficient Approximations for Matrix-based Renyi's Entropy
The recently developed matrix based Renyi's entropy enables measurement of information in data simply using the eigenspectrum of symmetric positive semi definite (PSD) matrices in reproducing kernel Hilbert space, without estimation of the underlying data distribution.
All You Need is RAW: Defending Against Adversarial Attacks with Camera Image Pipelines
Various defense methods have proposed image-to-image mapping methods, either including these perturbations in the training process or removing them in a preprocessing denoising step.
Markov subsampling based Huber Criterion
Subsampling is an important technique to tackle the computational challenges brought by big data.
Regularized Modal Regression on Markov-dependent Observations: A Theoretical Assessment
Our results show that the Markov dependence impacts on the generalization error in the way that sample size would be discounted by a multiplicative factor depending on the spectral gap of underlying Markov chain.
TNTC: two-stream network with transformer-based complementarity for gait-based emotion recognition
A new transformer-based complementarity module (TCM) is proposed to bridge the complementarity between two streams hierarchically via capturing long range dependencies.
There are free lunches
In this paper we propose a novel idea, "There are free lunches" (TAFL) Theorem, which states that some algorithms can achieve the best performance in all possible tasks, in the condition that tasks are given in a specific order.
Object Tracking by Jointly Exploiting Frame and Event Domain
Our approach's effectiveness is enforced by a novel designed cross-domain attention schemes, which can effectively enhance features based on self- and cross-domain attention schemes; The adaptiveness is guarded by a specially designed weighting scheme, which can adaptively balance the contribution of the two domains.
Ranked #3 on
Object Tracking
on FE108
Luminance Attentive Networks for HDR Image and Panorama Reconstruction
Based on this observation, we propose a novel normalization method called " HDR calibration " for HDR images stored in relative luminance, calibrating HDR images into a similar luminance scale according to the LDR images.
Polyp-PVT: Polyp Segmentation with Pyramid Vision Transformers
Unlike existing CNN-based methods, we adopt a transformer encoder, which learns more powerful and robust representations.
Ranked #9 on
Medical Image Segmentation
on CVC-ColonDB
Multi-domain Collaborative Feature Representation for Robust Visual Object Tracking
Jointly exploiting multiple different yet complementary domain information has been proven to be an effective way to perform robust object tracking.
Depth-Aware Mirror Segmentation
To exploit depth information in mirror segmentation, we first construct a large-scale RGB-D mirror segmentation dataset, which we subsequently employ to train a novel depth-aware mirror segmentation framework.
Multi-modal Trajectory Prediction for Autonomous Driving with Semantic Map and Dynamic Graph Attention Network
Predicting future trajectories of surrounding obstacles is a crucial task for autonomous driving cars to achieve a high degree of road safety.
Towards Accurate RGB-D Saliency Detection with Complementary Attention and Adaptive Integration
In this paper, we propose Complementary Attention and Adaptive Integration Network (CAAI-Net), a novel RGB-D saliency detection model that integrates complementary attention based feature concentration and adaptive cross-modal feature fusion into a unified framework for accurate saliency detection.
Accurate Camouflaged Object Detection via Mixture Convolution and Interactive Fusion
Our method detects camouflaged objects with an effective fusion strategy, which aggregates the rich context information from a large receptive field.
A Boundary Regression Model for Nested Named Entity Recognition
Then, a regression operation is introduced to regress boundaries of NEs in a sentence.
DWMD: Dimensional Weighted Orderwise Moment Discrepancy for Domain-specific Hidden Representation Matching
Our metric function takes advantage of a series for high-order moment alignment, and we theoretically prove that our DWMD metric function is error-free, which means that it can strictly reflect the distribution differences between domains and is valid without any feature distribution assumption.
Automatic Assessment of Full Left Ventricular Coverage in Cardiac Cine Magnetic Resonance Imaging with Fisher-Discriminative 3D CNN
Full coverage of the left ventricle (LV), from base to apex, is a basic criterion for CMR image quality and necessary for accurate measurement of cardiac volume and functional assessment.
A Transfer Learning based Feature-Weak-Relevant Method for Image Clustering
What's more, the handcrafted features are used to boot up the clustering process, and just have a little effect on the final performance; therefore, the proposed method is feature-weak-relevant.
An Explainable Adversarial Robustness Metric for Deep Learning Neural Networks
Instead of simply measuring a DNN's adversarial robustness in the input domain, as previous works, the proposed NSS is built on top of insightful mathematical understanding of the adversarial attack and gives a more explicit explanation of the robustness.
Scattering Parameters and Surface Normals from Homogeneous Translucent Materials using Photometric Stereo
This paper proposes a novel photometric stereo solution to jointly estimate surface normals and scattering parameters from a globally planar, homogeneous, translucent object.
