• Home
  • Search
  • Transformer Based Multi-Grained Features for Unsupervised Person Re-Identification
  • Open Access IconOpen Access
  • Cite Icon41
  • https://doi.org/10.1109/wacvw58289.2023.00009Copy DOI Icon

Transformer Based Multi-Grained Features for Unsupervised Person Re-Identification

  • Jan 1, 2023
  • Jiachen Li +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Multi-grained features extracted from convolutional neural networks (CNNs) have demonstrated their strong dis-crimination ability in supervised person re-identification (Re-ID) tasks. Inspired by them, this work investigates the way of extracting multi-grained features from a pure transformer network to address the unsupervised Re-ID problem that is label-free but much more challenging. To this end, we build a dual-branch network architecture based upon a modified Vision Transformer (ViT). The local tokens output in each branch are reshaped and then uniformly partitioned into multiple stripes to generate part-level features, while the global tokens of two branches are averaged to produce a global feature. Further, based upon offline-online associated camera-aware proxies (02CAP) that is a top-performing unsupervised Re-ID method, we define offline and online contrastive learning losses with respect to both global and part-level features to conduct unsupervised learning. Extensive experiments on three person Re-ID datasets show that the proposed method outperforms state-of-the-art unsupervised methods by a considerable margin, greatly mitigating the gap to supervised counterparts. Code will be available soon at https://github.com/RikoLi/WACV23-workshop-TMGF.

Similar Papers
  • Research Article
  • Citations4

Camera-Aware Differentiated Clustering With Focal Contrastive Learning for Unsupervised Vehicle Re-Identification

  • Oct 01, 2024
  • IEEE Transactions on Circuits and Systems for Video Technology
  • Mingkai Qiu +3
  • Research Article
  • Citations27

Relation-Preserving Feature Embedding for Unsupervised Person Re-Identification

  • Jan 01, 2024
  • IEEE Transactions on Multimedia
  • Xueping Wang +5
  • Research Article
  • Citations8

Unsupervised Learning of Intrinsic Semantics with Diffusion Model for Person Re-Identification.

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

ViTC-UReID: Enhancing unsupervised person ReID with vision transformer image encoder and camera-aware proxy learning

  • Sep 23, 2025
  • Journal of Computer Science and Cybernetics
  • Hai Dang Pham +2
  • Research Article

Silhouette-Driven Contrastive Learning with Hierarchical Neighborhood Structure for Unsupervised Clothes Change Person Re-Identification

  • Oct 01, 2025
  • CAAI Artificial Intelligence Research
  • Mingkun Li +1
  • Conference Article
  • Citations36

Learning Discriminative and Generalizable Representations by Spatial-Channel Partition for Person Re-Identification

  • Nov 21, 2019
  • Hao Chen +2
  • Research Article

Unsupervised Person Reidentification Using Stripe‐Driven Fusion Transformer Network

  • Jan 01, 2025
  • IET Software
  • Zeyu Zang +4
  • Research Article
  • Citations9

Imitating targets from all sides: an unsupervised transfer learning method for person re-identification

  • Apr 02, 2021
  • International Journal of Machine Learning and Cybernetics
  • Jiajie Tian +4
  • Research Article
  • Citations8

ADT: Person re-identification based on efficient attention mechanism and single-channel dual-channel fusion with transformer features aggregation

  • Oct 05, 2024
  • Expert Systems With Applications
  • Jiahui Xing +3
  • Research Article
  • Citations7

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

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

Camera Style Alignment for Unsupervised Person Re-Identification

  • Jan 01, 2025
  • IEICE Transactions on Information and Systems
  • Jifeng Guo +4
  • Research Article
  • Citations15

A review on video person re-identification based on deep learning

  • Aug 28, 2024
  • Neurocomputing
  • Haifei Ma +5
  • Conference Article
  • Citations1

A Survey of Person Re-identification Based on Deep Learning

  • Oct 15, 2021
  • Zimin Tian +3
  • Research Article
  • Citations5

Person re-identification based on frequency channel attention networks under the surveillance scenario

  • Jul 01, 2021
  • Journal of Physics: Conference Series
  • Shengbo Chen +1
  • Conference Article
  • Citations143

Unsupervised Person Re-Identification by Camera-Aware Similarity Consistency Learning

  • Oct 01, 2019
  • Ancong Wu +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.