mlsanityData to 14 Oct 2026

Unsupervised Long-Term Person Re-Identification with Clothes Change

arXiv 2202.03087 ↗First posted 7 Feb 2022cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

We investigate unsupervised person re-identification (Re-ID) with clothes change, a new challenging problem with more practical usability and scalability to real-world deployment. Most existing re-id methods artificially assume the clothes of every single person to be stationary across space and time. This condition is mostly valid for short-term re-id scenarios since an average person would often change the clothes even within a single day. To alleviate this assumption, several recent works have introduced the clothes change facet to re-id, with a focus on supervised learning person identity discriminative representation with invariance to clothes changes. Taking a step further towards this long-term re-id direction, we further eliminate the requirement of person identity labels, as they are significantly more expensive and more tedious to annotate in comparison to short-term person re-id datasets. Compared to conventional unsupervised short-term re-id, this new problem is drastically more challenging as different people may have similar clothes whilst the same person can wear multiple suites of clothes over different locations and times with very distinct appearance. To overcome such obstacles, we introduce a novel Curriculum Person Clustering (CPC) method that can adaptively regulate the unsupervised clustering criterion according to the clustering confidence. Experiments on three long-term person re-id datasets show that our CPC outperforms SOTA unsupervised re-id methods and even closely matches the supervised re-id models.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 37 of its 56 references that are in the map. First posted on arXiv 7 Feb 2022.

Builds on

37 of 56 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2016Densely Connected Convolutional Networkscited by 6,720
  5. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  6. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  7. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  8. 2020Deep Learning for Person Re-identification: A Survey and Outlookcited by 549
  9. 2017Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)cited by 473
  10. 2019On The Power of Curriculum Learning in Training Deep Networkscited by 286
  11. 2020Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identificationcited by 215
  12. 2020Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-IDcited by 212
25 more
  1. 2018Harmonious Attention Network for Person Re-Identificationcited by 211
  2. 2019A Strong Baseline and Batch Normalization Neck for Deep Person Re-identificationcited by 155
  3. 2020Automatic Curriculum Learning For Deep RL: A Short Surveycited by 150
  4. 2019Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identificationcited by 133
  5. 2019Relation-Aware Global Attention for Person Re-identificationcited by 124
  6. 2020Identity-Guided Human Semantic Parsing for Person Re-Identificationcited by 118
  7. 2020Person Re-identification by Contour Sketch under Moderate Clothing Changecited by 91
  8. 2021Cluster Contrast for Unsupervised Person Re-Identificationcited by 89
  9. 2020Long-Term Cloth-Changing Person Re-identificationcited by 85
  10. 2020AD-Cluster: Augmented Discriminative Clustering for Domain Adaptive Person Re-identificationcited by 81
  11. 2015Variance Reduction in SGD by Distributed Importance Samplingcited by 79
  12. 2020Unsupervised Person Re-identification via Softened Similarity Learningcited by 75
  13. 2019Learning Generalisable Omni-Scale Representations for Person Re-Identificationcited by 74
  14. 2018FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identificationcited by 71
  15. 2018Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-Identificationcited by 62
  16. 2019Unsupervised Tracklet Person Re-Identificationcited by 55
  17. 2019Unsupervised Person Re-identification by Soft Multilabel Learningcited by 53
  18. 2020When Person Re-identification Meets Changing Clothescited by 51
  19. 2018Unsupervised Person Re-identification by Deep Learning Tracklet Associationcited by 45
  20. 2016Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identificationcited by 41
  21. 2019Asymmetric Co-Teaching for Unsupervised Cross Domain Person Re-Identificationcited by 37
  22. 2017Person Re-Identification by Camera Correlation Aware Feature Augmentationcited by 35
  23. 2021Cluster-guided Asymmetric Contrastive Learning for Unsupervised Person Re-Identificationcited by 18
  24. 2020Intra-Camera Supervised Person Re-Identificationcited by 11
  25. 2020Learning Shape Representations for Clothing Variations in Person Re-Identificationcited by 10

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023Unsupervised Gait Recognition with Selective Fusioncited by 1