• Home
  • Search
  • Graph-Based Self-Learning for Robust Person Re-identification
  • Cite Icon7
  • https://doi.org/10.1109/wacv56688.2023.00477Copy DOI Icon

Graph-Based Self-Learning for Robust Person Re-identification

  • Jan 1, 2023
  • Yuqiao Xian +4 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Existing deep learning approaches for person re-identification (Re-ID) mostly rely on large-scale and well-annotated training data. However, human-annotated labels are prone to label noise in real-world applications. Previous person Re-ID works mainly focus on random label noise, which doesn’t properly reflect the characteristic of label noise in practical human-annotated process. In this work, we find the visual ambiguity noise is more common and reasonable noise assumption in annotation of person Re-ID. To handle the kind of noise, we propose a simple and effective robust person Re-ID framework, namely Graph-Based Self-Learning (GBSL), to iteratively learn discriminative representation and rectify noisy labels with limited annotated samples for each identity. Meanwhile, considering the practical annotation process in person Re-ID, we further extend the visual ambiguity noise assumption and propose a type of more practical label noise in person Re-ID, namely the tracklet-level label noise (TLN). Without modifying network architecture or loss function, our approach significantly improves the robustness against label noise of the Re-ID system. Our model obtains competitive performance with training data corrupted by various types of label noise and outperforms the existing methods for robust Re-ID on public benchmarks.

Similar Papers
  • Research Article
  • Citations102

Collaborative Refining for Person Re-Identification With Label Noise.

  • Jan 01, 2022
  • IEEE Transactions on Image Processing
  • Mang Ye +5
  • Conference Article
  • Citations2

Making Deep Neural Networks Robust to Label Noise: A Reweighting Loss and Data Filtration

  • Jul 01, 2019
  • Zhengwen Zhang +3
  • Research Article
  • Citations702

Deep learning with noisy labels: Exploring techniques and remedies in medical image analysis.

  • Jun 20, 2020
  • Medical image analysis
  • Davood Karimi +3
  • Research Article
  • Citations98

PurifyNet: A Robust Person Re-Identification Model With Noisy Labels

  • Jan 01, 2020
  • IEEE Transactions on Information Forensics and Security
  • Mang Ye +1
  • Book Chapter
  • Citations8

Effect of Label Noise on Robustness of Deep Neural Network Object Detectors

  • Jan 01, 2021
  • Bishwo Adhikari +4
  • Research Article
  • Citations46

On the Effects of Different Types of Label Noise in Multi-Label Remote Sensing Image Classification

  • Jan 01, 2022
  • IEEE Transactions on Geoscience and Remote Sensing
  • Tom Burgert +2
  • Conference Article
  • Citations2

Label-Noise Robust Person Re-Identification via Symmetric Learning

  • Jul 01, 2021
  • Wen Peng +5
  • Conference Article
  • Citations5

Neighborhood Information-Based Label Refinement for Person Re-Identification with Label Noise

  • Jun 04, 2023
  • Xian Zhong +5
  • Research Article
  • Citations29

BadLabel: A Robust Perspective on Evaluating and Enhancing Label-Noise Learning.

  • Jun 01, 2024
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Jingfeng Zhang +6
  • Research Article
  • Citations15

Refining Noisy Labels With Label Reliability Perception for Person Re-Identification

  • Jan 01, 2023
  • IEEE Transactions on Multimedia
  • Yongchun Chen +5
  • Conference Article
  • Citations173

Distilling Effective Supervision From Severe Label Noise

  • Jun 01, 2020
  • Zizhao Zhang +4
  • Conference Article
  • Citations167

Robust Person Re-Identification by Modelling Feature Uncertainty

  • Oct 01, 2019
  • Tianyuan Yu +4
  • Research Article
  • Citations2

Contrastive learning enhanced pseudo-labeling for unsupervised domain adaptation in person re-identification

  • Jul 14, 2025
  • PLOS One
  • Xuemei Bai +3
  • Research Article
  • Citations9

Learning Student Network Under Universal Label Noise.

  • Jan 01, 2024
  • IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
  • Jialiang Tang +4
  • Research Article
  • Citations15

Multi-category classification with label noise by robust binary loss

  • Jan 19, 2022
  • Neurocomputing
  • Defu Liu +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.