• Home
  • Search
  • Self-Supervised Person Re-Identification with Channel-Wise Transformer
  • Cite Icon4
  • https://doi.org/10.1109/bigdata55660.2022.10020632Copy DOI Icon

Self-Supervised Person Re-Identification with Channel-Wise Transformer

  • Dec 17, 2022
  • Zian Ye +3 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Unsupervised domain adaptive (UDA) person Re-Identification aims to improve the model’s generalization capability from labeled source domain to unlabeled target domain. To this end, a strong and robust method is required to extract discriminative features of pedestrians. Recently, transformer-based method achieves great performance on person Re-Identification (ReID). However, due to the domain gap between ImageNet and ReID datasets, it requires a large pre-training dataset to boost performance on Vision Transformer (ViT). To this end, we first investigate self-supervised learning methods with ViTs pretrained on LUPerson datasets, and find it significantly outperforms ImageNet supervised pre-training models on ReID tasks. A Catastrophic Forgetting Score (CFS) is also used to select a subset of LUPerson, which reduces the training time and improves performance. We then proposed a channel-wise self-attention module to reduce the computing cost on the class token. A dual prototype contrastive learning is proposed to fully exploit the hard feature on memory bank under unsupervised domain adaptation. Finally, we achieve state-of-the-art performance on Market-1501 and MSMT17. Our model achieves 91.5%/69.6% mAP accuracy on Market-1501/MSMT17 for supervised ReID, and 90.7%/57.4% mAP for MS2MA/MA2MS UDA ReID.

Similar Papers
  • Research Article
  • Citations16

Dual Prototype Contrastive learning with Fourier Generalization for Domain Adaptive Person Re-identification

  • Sep 05, 2022
  • Knowledge-Based Systems
  • Xulin Song +2
  • Conference Article
  • Citations193

Unsupervised Pre-training for Person Re-identification

  • Jun 01, 2021
  • Dengpan Fu +7
  • Research Article
  • Citations19

Cluster-based Dual-branch Contrastive Learning for unsupervised domain adaptation person re-identification

  • Sep 29, 2023
  • Knowledge-Based Systems
  • Qing Tian +1
  • 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
  • Citations21

Source-free Style-diversity Adversarial Domain Adaptation with Privacy-preservation for person re-identification

  • Nov 04, 2023
  • Knowledge-Based Systems
  • Xiaofeng Qu +4
  • Conference Article
  • Citations1

Foggy Person Re-Identification based on Adaptive Recognition of Fog Attributes

  • Nov 17, 2023
  • Mengjiao Li +3
  • Research Article
  • Citations7

Two-phase self-supervised pretraining for object re-identification

  • Dec 22, 2022
  • Knowledge-Based Systems
  • Haoyan Ma +3
  • Conference Article
  • Citations14

Camera Alignment and Weighted Contrastive Learning for Domain Adaptation in Video Person ReID

  • Jan 01, 2023
  • Djebril Mekhazni +4
  • Research Article

Mini-transformer with pooling for unsupervised domain adaptation person reidentification

  • Oct 06, 2022
  • Journal of Electronic Imaging
  • Lei Ma +2
  • Research Article
  • Citations9

Nighttime Person Re-Identification via Collaborative Enhancement Network With Multi-Domain Learning

  • Jan 01, 2025
  • IEEE Transactions on Information Forensics and Security
  • Andong Lu +5
  • Conference Article
  • Citations6

Survey on Unsupervised Techniques for Person Re-Identification

  • Jan 01, 2021
  • Changshui Yang +2
  • Conference Article
  • Citations23

BV-Person: A Large-scale Dataset for Bird-view Person Re-identification

  • Oct 01, 2021
  • Cheng Yan +6
  • Research Article
  • Citations102

Part-aware Progressive Unsupervised Domain Adaptation for Person Re-Identification

  • Jun 15, 2020
  • IEEE Transactions on Multimedia
  • Fan Yang +8
  • Book Chapter
  • Citations73

PASS: Part-Aware Self-Supervised Pre-Training for Person Re-Identification

  • Jan 01, 2022
  • Kuan Zhu +5
  • Research Article
  • Citations30

Multi-Prompts Learning with Cross-Modal Alignment for Attribute-Based Person Re-identification

  • Mar 24, 2024
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Yajing Zhai +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.