• Home
  • Search
  • Improving Consistency of Proxy-Level Contrastive Learning for Unsupervised Person Re-Identification
  • Cite Icon10
  • https://doi.org/10.1109/tifs.2024.3426351Copy DOI Icon

Improving Consistency of Proxy-Level Contrastive Learning for Unsupervised Person Re-Identification

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Recently, contrastive learning-based unsupervised person re-identification (Re-ID) methods have garnered significant attention due to their effectiveness. These methods rely on predicted pseudo-labels to construct contrastive pairs, optimizing the network gradually. Some methods also utilize camera labels to explore intra-camera and inter-camera contrastive relations, achieving state-of-the-art results. However, these methods fail to address the issue of inconsistency in proxy-level contrastive learning, which arises from variations in the distribution of instances belonging to the same proxy. Specifically, they are sensitive to the distribution of instances in a mini-batch used for contrastive pair construction, and uncertainty or noise in the data distribution can lead to turbulence in the contrastive loss, degrading the effectiveness of contrastive learning. In this work, we first propose a dual-branch contrastive learning (DBCL) framework. The framework comprises a dual-branch structure with an identity discrimination branch and a camera view awareness branch. These branches are mutually trained to produce a jointly optimized model with both high person identification accuracy and cross-camera robustness. Moreover, to mitigate the proxy-level contrastive inconsistency issue in the camera view awareness branch, we design intra-camera and inter-camera consistent contrastive losses. Our DBCL has been extensively evaluated on several person Re-ID datasets and has demonstrated superior performance compared to state-of-the-art methods. Notably, on the challenging MSMT17 dataset with complex scenes, our method achieved an mAP of 45.3% and Rank-1 accuracy of 75.3%.

Similar Papers
  • Research Article
  • Citations59

Offline-Online Associated Camera-Aware Proxies for Unsupervised Person Re-Identification.

  • Jan 01, 2022
  • IEEE Transactions on Image Processing
  • Menglin Wang +4
  • Research Article
  • Citations34

Camera Invariant Feature Learning for Unsupervised Person Re-Identification

  • Jan 01, 2023
  • IEEE Transactions on Multimedia
  • Zhiqi Pang +3
  • Research Article
  • Citations21

Fully Unsupervised Person Re-Identification via Selective Contrastive Learning

  • Feb 16, 2022
  • ACM Transactions on Multimedia Computing, Communications, and Applications
  • Bo Pang +3
  • Research Article
  • Citations9

Multi-granularity Pseudo-label Collaboration for unsupervised person re-identification

  • Dec 05, 2022
  • Computer Vision and Image Understanding
  • Xiaobao Li +3
  • Research Article
  • Citations4

Domain Adaptive Learning with Multi-Granularity Features for Unsupervised Person Re-identification

  • Jan 05, 2022
  • Chinese Journal of Electronics
  • Lihua Fu +5
  • PDF
  • Research Article
  • Citations5

Unsupervised Joint Contrastive Learning for Aerial Person Re-Identification and Remote Sensing Image Classification

  • Jan 22, 2024
  • Remote Sensing
  • Guoqing Zhang +2
  • Research Article
  • Citations94

Semantic-Aware Occlusion-Robust Network for Occluded Person Re-Identification

  • Oct 22, 2020
  • IEEE Transactions on Circuits and Systems for Video Technology
  • Xiaokang Zhang +4
  • Research Article
  • Citations14

Discriminative Identity-Feature Exploring and Differential Aware Learning for Unsupervised Person Re-Identification

  • Jan 01, 2024
  • IEEE Transactions on Multimedia
  • Yuxuan Liu +4
  • Research Article
  • Citations115

Cluster-Guided Asymmetric Contrastive Learning for Unsupervised Person Re-Identification

  • Jan 01, 2022
  • IEEE Transactions on Image Processing
  • Mingkun Li +2
  • Conference Article
  • Citations2

Pose-guided feature fusion for occluded unsupervised person re-identification

  • Oct 19, 2022
  • Binquan Wang +2
  • Research Article
  • Citations5

Multiple camera styles learning for unsupervised person re-identification

  • Feb 25, 2023
  • Optik
  • Linbing He +3
  • PDF
  • Research Article
  • Citations16

CCSD: cross-camera self-distillation for unsupervised person re-identification

  • Nov 15, 2023
  • Visual Intelligence
  • Jiyuan Chen +3
  • Conference Article
  • Citations45

Hard-sample Guided Hybrid Contrast Learning for Unsupervised Person Re-Identification

  • Nov 17, 2021
  • Zheng Hu +2
  • Research Article

Unsupervised Person Reidentification Using Stripe‐Driven Fusion Transformer Network

  • Jan 01, 2025
  • IET Software
  • Zeyu Zang +4
  • Conference Article
  • Citations277

ICE: Inter-instance Contrastive Encoding for Unsupervised Person Re-identification

  • Oct 01, 2021
  • Hao Chen +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.