• Home
  • Search
  • Knowledge Compensation Network with Divisible Feature Learning for Unsupervised Domain Adaptive Person Re-identification
  • https://doi.org/10.1007/978-3-030-89363-7_36Copy DOI Icon

Knowledge Compensation Network with Divisible Feature Learning for Unsupervised Domain Adaptive Person Re-identification

  • Jan 1, 2021
  • Jiajing Hong +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

Due to the large domain shift and the discriminative feature learning with unlabeled datasets, unsupervised domain adaptation (UDA) for person re-identification (re-ID) still remains a challenging task. Some current methods adopt a clustering-based strategy to assign pseudo labels to the unlabeled samples in target domains for classification. However, the rich knowledge of the model in different training stages is not fully utilized in those methods and the pseudo labels generated by clustering algorithms inevitably contain noise, which would limit the performance of re-ID models. To tackle this problem, a Knowledge Compensation Network with Divisible feature learning (KCND) is proposed in this paper, which aggregates the past-to-present knowledge of models from training samples for discriminative feature learning and resists the label noise produced by clustering. Also, a novel compensation-guided softened loss is developed to enhance the generalization and robustness of re-ID models. Our experimental results on large-scale datasets (Market-1501, DukeMTMC-reID and MSMT17) have demonstrated the performance of KCND is better than other methods in terms of the mAP and CMC accuracy.

Similar Papers
  • Research Article
  • Citations10

Unsupervised domain adaptation via discriminative feature learning and classifier adaptation from center-based distances

  • May 16, 2022
  • Knowledge-Based Systems
  • Lei Li +4
  • Research Article
  • Citations5

Unsupervised cross-domain person re-identification with self-attention and joint-flexible optimization

  • Apr 30, 2021
  • Image and Vision Computing
  • Haopeng Hou +6
  • Conference Article

Hierarchical clustering via mutual learning for unsupervised person re-identification

  • Mar 07, 2021
  • Xu Xu +3
  • Conference Article

Unsupervised confident co-promoting: refinery for pseudo labels on unsupervised person re-identification

  • Oct 13, 2022
  • Hao Tang +1
  • Research Article

Discriminative transfer feature learning for unsupervised domain adaptation.

  • Jul 09, 2026
  • Neural networks : the official journal of the International Neural Network Society
  • Mengyao Li +2
  • Research Article
  • Citations23

Learning domain invariant and specific representation for cross-domain person re-identification

  • Jan 07, 2021
  • Applied Intelligence
  • Yanwen Chong +5
  • Conference Article
  • Citations6

Survey on Unsupervised Techniques for Person Re-Identification

  • Jan 01, 2021
  • Changshui Yang +2
  • 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
  • Citations13

EXAM: A Framework of Learning Extreme and Moderate Embeddings for Person Re-ID

  • Jan 07, 2021
  • Journal of Imaging
  • Guanqiu Qi +5
  • Conference Article
  • Citations21

Learning Discriminative Geodesic Flow Kernel for Unsupervised Domain Adaptation

  • Jul 01, 2018
  • Jianre Wei +3
  • Research Article
  • Citations85

Complementary Pseudo Labels for Unsupervised Domain Adaptation On Person Re-Identification.

  • Jan 01, 2021
  • IEEE Transactions on Image Processing
  • Hao Feng +5
  • Conference Article
  • Citations132

Discriminative Feature Learning With Consistent Attention Regularization for Person Re-Identification

  • Oct 01, 2019
  • Sanping Zhou +3
  • Research Article
  • Citations6

Discriminative transfer feature learning based on robust-centers

  • May 18, 2022
  • Neurocomputing
  • Lei Li +3
  • PDF
  • Research Article
  • Citations12

Noise Resistible Network for Unsupervised Domain Adaptation on Person Re-Identification

  • Jan 01, 2021
  • IEEE Access
  • Suian Zhang +3
  • Research Article
  • Citations19

Transfer easy to hard: Adversarial contrastive feature learning for unsupervised person re-identification

  • Sep 16, 2023
  • Pattern Recognition
  • Haoxuanye Ji +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.