mlsanityData to 14 Oct 2026

Dual Cluster Contrastive learning for Object Re-Identification

arXiv 2112.04662 ↗First posted 9 Dec 2021cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Recently, cluster contrastive learning has been proven effective for object ReID by computing the contrastive loss between the individual features and the cluster memory. However, existing methods that use the individual features to momentum update the cluster memory will fluctuate over the training examples, especially for the outlier samples. Unlike the individual-based updating mechanism, the centroid-based updating mechanism that applies the mean feature of each cluster to update the cluster memory can reduce the impact of individual samples. Therefore, we formulate the individual-based updating and centroid-based updating mechanisms in a unified cluster contrastive framework, named Dual Cluster Contrastive framework (DCC), which maintains two types of memory banks: individual and centroid cluster memory banks. Significantly, the individual cluster memory considers just one individual at a time to take a single step for updating. The centroid cluster memory applies the mean feature of each cluster to update the corresponding cluster memory. During optimization, besides the vallina contrastive loss of each memory, a cross-view consistency constraint is applied to exchange the benefits of two memories for generating a discriminative description for the object ReID. Note that DCC can be easily applied for unsupervised or supervised object ReID by using ground-truth labels or the generated pseudo-labels. Extensive experiments on three benchmarks, e.g., Market-1501, MSMT17, and VeRi-776, under supervised Object ReID and unsupervised Object ReID demonstrate the superiority of the proposed DCC.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 51 of its 68 references that are in the map. First posted on arXiv 9 Dec 2021.

Builds on

51 of 68 references.

References · 51

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  4. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  5. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  6. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,845
  7. 2017Person Transfer GAN to Bridge Domain Gap for Person Re-Identificationcited by 480
  8. 2021TransReID: Transformer-based Object Re-Identificationcited by 435
  9. 2019Bag of Tricks and A Strong Baseline for Deep Person Re-identificationcited by 430
  10. 2020Circle Loss: A Unified Perspective of Pair Similarity Optimizationcited by 403
  11. 2019Omni-Scale Feature Learning for Person Re-Identificationcited by 295
  12. 2018Learning Discriminative Features with Multiple Granularities for Person Re-Identificationcited by 291
38 more
  1. 2017Improved Texture Networks: Maximizing Quality and Diversity in Feed-forward Stylization and Texture Synthesiscited by 215
  2. 2020Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identificationcited by 215
  3. 2019Joint Discriminative and Generative Learning for Person Re-identificationcited by 213
  4. 2020Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-IDcited by 212
  5. 2016Joint Detection and Identification Feature Learning for Person Searchcited by 190
  6. 2017Beyond triplet loss: a deep quadruplet network for person re-identificationcited by 172
  7. 2020FastReID: A Pytorch Toolbox for General Instance Re-identificationcited by 166
  8. 2019Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identificationcited by 133
  9. 2019ABD-Net: Attentive but Diverse Person Re-Identificationcited by 126
  10. 2019Relation-Aware Global Attention for Person Re-identificationcited by 124
  11. 2021Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identificationcited by 114
  12. 2021Cluster Contrast for Unsupervised Person Re-Identificationcited by 89
  13. 2019Hierarchical Clustering with Hard-batch Triplet Loss for Person Re-identificationcited by 83
  14. 2021ICE: Inter-instance Contrastive Encoding for Unsupervised Person Re-identificationcited by 69
  15. 2019Mixed High-Order Attention Network for Person Re-Identificationcited by 65
  16. 2020Joint Generative and Contrastive Learning for Unsupervised Person Re-identificationcited by 58
  17. 2021Group-aware Label Transfer for Domain Adaptive Person Re-identificationcited by 58
  18. 2020Multiple Expert Brainstorming for Domain Adaptive Person Re-identificationcited by 56
  19. 2019Self-training with progressive augmentation for unsupervised cross-domain person re-identificationcited by 55
  20. 2019Unsupervised Person Re-identification by Soft Multilabel Learningcited by 53
  21. 2020Parsing-based View-aware Embedding Network for Vehicle Re-Identificationcited by 53
  22. 2021IDM: An Intermediate Domain Module for Domain Adaptive Person Re-IDcited by 51
  23. 2021Refining Pseudo Labels with Clustering Consensus over Generations for Unsupervised Object Re-identificationcited by 45
  24. 2020The Devil is in the Details: Self-Supervised Attention for Vehicle Re-Identificationcited by 39
  25. 2019Second-order Non-local Attention Networks for Person Re-identificationcited by 38
  26. 2020Exploring Spatial Significance via Hybrid Pyramidal Graph Network for Vehicle Re-identificationcited by 37
  27. 2020Uncertainty-Aware Multi-Shot Knowledge Distillation for Image-Based Object Re-Identificationcited by 32
  28. 2020Self-supervised Geometric Features Discovery via Interpretable Attention for Vehicle Re-Identification and Beyondcited by 25
  29. 2021Heterogeneous Relational Complement for Vehicle Re-identificationcited by 25
  30. 2021Towards Discriminative Representation Learning for Unsupervised Person Re-identificationcited by 20
  31. 2020Multi-Domain Learning and Identity Mining for Vehicle Re-Identificationcited by 19
  32. 2021Cluster-guided Asymmetric Contrastive Learning for Unsupervised Person Re-Identificationcited by 18
  33. 2020Domain Adaptive Person Re-Identification via Coupling Optimizationcited by 13
  34. 2020Looking GLAMORous: Vehicle Re-Id in Heterogeneous Cameras Networks with Global and Local Attentioncited by 10
  35. 2019Part-Guided Attention Learning for Vehicle Instance Retrievalcited by 9
  36. 2017Large Margin Learning in Set to Set Similarity Comparison for Person Re-identificationcited by 7
  37. 2019Domain Adaptive Attention Learning for Unsupervised Person Re-Identificationcited by 7
  38. 2020Cluster-level Feature Alignment for Person Re-identificationcited by 3

50 most cited of 51 All 51 (JSON)

Built on by

Not cited yet.