Mind the Gap: Bridging Occlusion in Gait Recognition via Residual Gap Correction

• URL: http://arxiv.org/abs/2507.10978v2
• Date: Mon, 21 Jul 2025 23:49:15 GMT
• Title: Mind the Gap: Bridging Occlusion in Gait Recognition via Residual Gap Correction
• Authors: Ayush Gupta, Siyuan Huang, Rama Chellappa,
• Abstract summary: We propose RG-Gait, a method for residual correction for occluded gait recognition with holistic retention.<n>Our proposed network adaptively integrates the learned residual, significantly improving performance on occluded gait sequences.
• Score: 57.75544235445363
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Gait is becoming popular as a method of person re-identification because of its ability to identify people at a distance. However, most current works in gait recognition do not address the practical problem of occlusions. Among those which do, some require paired tuples of occluded and holistic sequences, which are impractical to collect in the real world. Further, these approaches work on occlusions but fail to retain performance on holistic inputs. To address these challenges, we propose RG-Gait, a method for residual correction for occluded gait recognition with holistic retention. We model the problem as a residual learning task, conceptualizing the occluded gait signature as a residual deviation from the holistic gait representation. Our proposed network adaptively integrates the learned residual, significantly improving performance on occluded gait sequences without compromising the holistic recognition accuracy. We evaluate our approach on the challenging Gait3D, GREW and BRIAR datasets and show that learning the residual can be an effective technique to tackle occluded gait recognition with holistic retention. We release our code publicly at https://github.com/Ayush-00/rg-gait.

Related papers

• GaitAdapt: Continual Learning for Evolving Gait Recognition [8.11771678547237]
  We present a continual gait recognition task, GaitAdapt, which supports the progressive enhancement of gait recognition capabilities over time.<n>We also propose GaitAdapter, a non-replay continual learning approach for gait recognition.<n>GitAdapter effectively retains gait knowledge acquired from diverse tasks, exhibiting markedly superior discriminative capability compared to alternative methods.
  arXiv  Detail & Related papers  (2025-08-05T12:26:52Z)
• EyeSeg: An Uncertainty-Aware Eye Segmentation Framework for AR/VR [58.33693755009173]
  EyeSeg is an uncertainty-aware eye segmentation framework for augmented reality (AR) and virtual reality (VR)<n>We show that EyeSeg achieves segmentation improvements of MIoU, E1, F1, and ACC surpassing previous approaches.
  arXiv  Detail & Related papers  (2025-07-13T14:33:10Z)
• MimicGait: A Model Agnostic approach for Occluded Gait Recognition using Correlational Knowledge Distillation [40.75942030089628]
  We propose MimicGait, a model-agnostic approach for gait recognition in the presence of occlusions.<n>We train the network using a multi-instance correlational distillation loss to capture both inter-sequence and intra-sequence correlations in the occluded gait patterns of a subject.<n>We demonstrate the effectiveness of our approach on challenging real-world datasets like GREW, Gait3D and BRIAR.
  arXiv  Detail & Related papers  (2025-01-26T20:23:44Z)
• Causality-inspired Discriminative Feature Learning in Triple Domains for Gait Recognition [36.55724380184354]
  We propose CLTD, a discriminative feature learning module designed to 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.
  arXiv  Detail & Related papers  (2024-07-17T12:16:44Z)
• You Can Run but not Hide: Improving Gait Recognition with Intrinsic Occlusion Type Awareness [48.151855620080134]
  Occluded body parts can affect gait recognition from uncontrolled outdoor sequences at range. Most current methods assume the availability of complete body information while extracting the gait features. We propose an occlusion aware gait recognition method which can be used to model intrinsic occlusion awareness into potentially any state-of-the-art gait recognition method.
  arXiv  Detail & Related papers  (2023-12-04T19:11:40Z)
• Magnitude Matters: Fixing SIGNSGD Through Magnitude-Aware Sparsification in the Presence of Data Heterogeneity [60.791736094073]
  Communication overhead has become one of the major bottlenecks in the distributed training of deep neural networks. We propose a magnitude-driven sparsification scheme, which addresses the non-convergence issue of SIGNSGD. The proposed scheme is validated through experiments on Fashion-MNIST, CIFAR-10, and CIFAR-100 datasets.
  arXiv  Detail & Related papers  (2023-02-19T17:42:35Z)
• Byzantine-Robust Learning on Heterogeneous Data via Gradient Splitting [58.91947205027892]
  Federated learning has exhibited vulnerabilities to Byzantine attacks. Byzantine attackers can send arbitrary gradients to a central server to destroy the convergence and performance of the global model. A wealth of robust AGgregation Rules (AGRs) have been proposed to defend against Byzantine attacks.
  arXiv  Detail & Related papers  (2023-02-13T03:31:50Z)
• Neighbour Consistency Guided Pseudo-Label Refinement for Unsupervised Person Re-Identification [80.98291772215154]
  Unsupervised person re-identification (ReID) aims at learning discriminative identity features for person retrieval without any annotations. Recent advances accomplish this task by leveraging clustering-based pseudo labels. We propose a Neighbour Consistency guided Pseudo Label Refinement framework.
  arXiv  Detail & Related papers  (2022-11-30T09:39:57Z)
• Holistic Guidance for Occluded Person Re-Identification [7.662745552551165]
  In real-world video surveillance applications, person re-identification (ReID) suffers from the effects of occlusions and detection errors. We introduce a novel Holistic Guidance (HG) method that relies only on person identity labels. Our proposed student-teacher framework is trained to address the problem by matching the distributions of between- and within-class distances (DCDs) of occluded samples with that of holistic (non-occluded) samples. In addition to this, a joint generative-discriminative backbone is trained with a denoising autoencoder, allowing the system to
  arXiv  Detail & Related papers  (2021-04-13T21:50:29Z)
• Learning from Self-Discrepancy via Multiple Co-teaching for Cross-Domain Person Re-Identification [12.106894735305714]
  We propose a multiple co-teaching framework for domain adaptive person re-ID. Our method achieves competitive performance compared with the state-of-the-arts.
  arXiv  Detail & Related papers  (2021-04-06T03:12:11Z)
• Exploiting Sample Uncertainty for Domain Adaptive Person Re-Identification [137.9939571408506]
  We estimate and exploit the credibility of the assigned pseudo-label of each sample to alleviate the influence of noisy labels. Our uncertainty-guided optimization brings significant improvement and achieves the state-of-the-art performance on benchmark datasets.
  arXiv  Detail & Related papers  (2020-12-16T04:09:04Z)
• Improving Face Recognition by Clustering Unlabeled Faces in the Wild [77.48677160252198]
  We propose a novel identity separation method based on extreme value theory. It greatly reduces the problems caused by overlapping-identity label noise. Experiments on both controlled and real settings demonstrate our method's consistent improvements.
  arXiv  Detail & Related papers  (2020-07-14T12:26:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.