Paper Reading AI Learner

Causality-inspired Discriminative Feature Learning in Triple Domains for Gait Recognition

2024-07-17 12:16:44
Haijun Xiong, Bin Feng, Xinggang Wang, Wenyu Liu

Abstract

Gait recognition is a biometric technology that distinguishes individuals by their walking patterns. However, previous methods face challenges when accurately extracting identity features because they often become entangled with non-identity clues. To address this challenge, we propose CLTD, a causality-inspired discriminative feature learning module designed to effectively eliminate the influence of confounders in triple domains, \ie, spatial, temporal, and spectral. Specifically, we utilize the Cross Pixel-wise Attention Generator (CPAG) to generate attention distributions for factual and counterfactual features in spatial and temporal domains. Then, we introduce the Fourier Projection Head (FPH) to project spatial features into the spectral space, which preserves essential information while reducing computational costs. Additionally, we employ an optimization method with contrastive learning to enforce semantic consistency constraints across sequences from the same subject. Our approach has demonstrated significant performance improvements on challenging datasets, proving its effectiveness. Moreover, it can be seamlessly integrated into existing gait recognition methods.

Abstract (translated)

步伐识别是一种生物识别技术,它通过区分个体的行走模式来识别个体。然而, previous 方法在准确提取身份特征时面临挑战,因为它们通常会纠缠于非个体特征。为解决这个挑战,我们提出了 CLTD,一种以因果关系为导向的判别特征学习模块,旨在有效消除在三个领域(即空间、时间和频域)中混淆因素的影响。具体来说,我们利用 Cross Pixel-wise Attention Generator (CPAG) 生成空间和时间域中的事实和反事实特征的注意力分布。然后,我们引入了 Fourier Projection Head (FPH),将空间特征投影到频域中,保留关键信息的同时降低计算成本。此外,我们还使用一种具有对比学习优化的方法来强制确保同一主题序列之间的语义一致性约束。我们的方法在具有挑战性的数据集上取得了显著的性能提升,证明了其有效性。此外,它可以轻松地集成到现有的步伐识别方法中。

URL

https://arxiv.org/abs/2407.12519

PDF

https://arxiv.org/pdf/2407.12519.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model LLM Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Robot Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Time_Series Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot