• Home
  • Search
  • Discriminative Identity-Feature Exploring and Differential Aware Learning for Unsupervised Person Re-Identification
  • Cite Icon14
  • https://doi.org/10.1109/tmm.2023.3268369Copy DOI Icon

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

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

Unsupervised person re-identification (Re-ID) aims to learn discriminative representations for person retrieval from unlabeled data. Currently, state-of-the-art techniques accomplish this task by using instance contrastive learning, which contrasts the similarities of the instances in different views. However, existing contrastive methods only focus on the positive effects of inter-instance relationships, while neglecting the negative effects of intra-instance redundancy information. This redundancy information can generate invalid or spurious intra-class relationships during the instance contrasting process, which enlarges the intra-class gaps and increases the noisy pseudo-labels. To address this issue, we propose a discriminative identity-feature exploring and differential aware learning (DiDAL) framework to learn more discriminative intra-identity representations. Specifically, the DiDAL extracts intra-instance salient features by synthetic complementary attention, and further explores the discriminative identity features by modeling the relationship among these salient features based on graph neural networks. This strategy aims to reduce the intra-instance redundancy information. Moreover, DiDAL explores hard instances by leveraging the extracted intra-instance salient features, and matches an anchor with multiple hard positive instances to enhance the robustness of the model to noisy pseudo-labels. Extensive experiment results on two widely used person re-identification datasets and a vehicle re-identification dataset demonstrate the superiority of the proposed method compared with existing state-of-the-art methods.

Similar Papers
  • Research Article

Recent progress in person re-ID

  • Jan 01, 2023
  • Journal of Image and Graphics
  • Zhang Yongfei +10
  • Conference Article
  • Citations193

Unsupervised Pre-training for Person Re-identification

  • Jun 01, 2021
  • Dengpan Fu +7
  • Conference Article
  • Citations2

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

  • Oct 19, 2022
  • Binquan Wang +2
  • 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

DCR: A Unified Framework for Holistic/Partial Person ReID

  • Jan 01, 2021
  • IEEE Transactions on Multimedia
  • Zan Gao +5
  • Research Article
  • Citations6

Learning Deep RGBT Representations for Robust Person Re-identification

  • Jan 19, 2021
  • International Journal of Automation and Computing
  • Ai-Hua Zheng +4
  • Conference Article
  • Citations7

Optimizing Federated Unsupervised Person Re-identification via Camera-aware Clustering

  • Sep 26, 2022
  • Jiabei Liu +4
  • Research Article
  • Citations10

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

  • Jan 01, 2024
  • IEEE Transactions on Information Forensics and Security
  • Yimin Liu +5
  • Research Article
  • Citations34

Camera Invariant Feature Learning for Unsupervised Person Re-Identification

  • Jan 01, 2023
  • IEEE Transactions on Multimedia
  • Zhiqi Pang +3
  • Conference Article
  • Citations45

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

  • Nov 17, 2021
  • Zheng Hu +2
  • Conference Article
  • Citations3

Unsupervised person re-identification via re-ranking enhanced sample-specific metric learning

  • Sep 01, 2017
  • Heng Zhao +3
  • PDF
  • Research Article
  • Citations27

A Multi-Attention Approach for Person Re-Identification Using Deep Learning

  • Apr 02, 2023
  • Sensors (Basel, Switzerland)
  • Shimaa Saber +4
  • Research Article
  • Citations4

Two‐level salient feature complementary network for person re‐identification

  • Jan 14, 2022
  • International Journal of Intelligent Systems
  • Haishun Du +4
  • Conference Article
  • Citations387

Unsupervised Person Re-Identification via Multi-Label Classification

  • Jun 01, 2020
  • Dongkai Wang +1
  • Research Article
  • Citations40

Unsupervised Person Re-Identification via Multi-Label Classification

  • Sep 20, 2022
  • International Journal of Computer Vision
  • Dongkai Wang +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.