/Awesome-Unsupervised-Person-Re-identification

Awesome-Unsupervised-Person-Re-identification

Awesome-Unsupervised-Person-Re-identificationAwesome

Contributing šŸ‘Š

Please help contribute this list by contacting me or add pull request šŸ˜

Markdown format:

- References. 
  [[pdf]](link) 
  [[code]](link)

KeyWords

Unsupervised Person Reidentification,Tranfer Learning,Domain Adaptation,Clustering

Table of Contents

Datasets

  • Awesome re-id dataset [github]
  • Market-1501 Leaderboard [page]
  • Duke Leaderboard [page]
  • Re-id dataset collection [page]

Methods

Benchmarks

UDA re-ID

Pure re-ID bechmarks

Paper list

Add five papers published in ICCV2021

  • Online Pseudo Label Generation by Hierarchical Cluster Dynamics for Adaptive Person Re-Identification[Paper]
  • ICE: Inter-Instance Contrastive Encoding for Unsupervised Person Re-Identification[Paper]
  • Meta Pairwise Relationship Distillation for Unsupervised Person Re-Identification[Paper]
  • Towards Discriminative Representation Learning for Unsupervised Person Re-Identification[Paper]
  • IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID[Paper]

Add some journal articles

  • Attribute-Aligned Domain-Invariant Feature Learning for Unsupervised Domain Adaptation Person Re-Identiļ¬cation(TIFS2021)
  • Complementary Pseudo Labels for Unsupervised Domain Adaptation On Person Re-Identiļ¬cation(TIP2021)
  • Domain Adaptive Person Re-Identiļ¬cation via Camera Style Generation and Label Propagation(TIFS2020)
  • Dynamic Graph Co-Matching for Unsupervised Video-Based Person Re-Identiļ¬cation(TIP2019)
  • End-to-End Domain Adaptive Attention Network for Cross-Domain Person Re-Identiļ¬cation(TIFS2021)
  • Hierarchical Connectivity-Centered Clustering for Unsupervised Domain Adaptation on Person Re-Identiļ¬cation(TIP2021)
  • Homogeneous-to-Heterogeneous: Unsupervised Learning for RGB-Infrared Person Re-Identiļ¬cation(TIP2021)
  • Unsupervised Domain Adaptation with Background Shift Mitigating for Person Re-Identiļ¬cation(IJCV2021)
  • Leveraging Virtual and Real Person for Unsupervised Person Re-Identiļ¬cation(TMM2020)
  • Part-aware Progressive Unsupervised Domain Adaptation for Person Re-Identiļ¬cation(TMM2021)
  • Progressive Unsupervised Person Re-Identiļ¬cation by Tracklet Association With Spatio-Temporal Regularization(TMM2021)
  • Self-Supervised Agent Learning for Unsupervised Cross-Domain Person Re-Identiļ¬cation(TIP2020)
  • Self-Training With Progressive Representation Enhancement for Unsupervised Cross-Domain Person Re-Identiļ¬cation(TIP2021)
  • Unsupervised Cross Domain Person Re-Identiļ¬cation by Multi-Loss Optimization Learning(TIP2021)
  • Unsupervised Person Re-identiļ¬cation via Cross-Camera Similarity Exploration(TIP2020)

The latest paper released in 2021

  • Refining Pseudo Labels With Clustering Consensus Over Generations for Unsupervised Object Re-Identification[Paper](CVPR2021)

  • Unsupervised Pre-Training for Person Re-Identification[Paper](CVPR2021)

  • Unsupervised Multi-Source Domain Adaptation for Person Re-Identification[Paper](CVPR2021)

  • Refining Pseudo Labels With Clustering Consensus Over Generations for Unsupervised Object Re-Identification[Paper](CVPR2021)

  • Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification[Paper](CVPR2021)

  • Joint Generative and Contrastive Learning for Unsupervised Person Re-Identification[Paper](CVPR2021)

  • Intra-Inter Camera Similarity for Unsupervised Person Re-Identification[Paper](CVPR2021)

  • Group-aware Label Transfer for Domain Adaptive Person Re-identification[Paper](CVPR2021)

  • Camera-Aware Proxies for Unsupervised Person Re-Identification[Paper](AAAI2021)

  • Unsupervised Domain Adaptation for Person Re-Identification via Heterogeneous Graph Alignment[Paper](AAAI2021)

  • Exploiting Sample Uncertainty for Domain Adaptive Person Re-Identification[Paper](AAAI2021)

Unsupervised Domain Adaptation

Domain style transfer or Data Augmentation

  • Li, Yu-Jhe, et al. "Cross-dataset person re-identification via unsupervised pose disentanglement and adaptation." Proceedings of the IEEE/CVF International Conference on Computer Vision. 2019.[Paper]

  • Liu, Jiawei, et al. "Adaptive transfer network for cross-domain person re-identification." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019.[Paper]

  • Zhong, Zhun, et al. "Camstyle: A novel data augmentation method for person re-identification." IEEE Transactions on Image Processing 28.3 (2018): 1176-1190.[Paper]

  • Zhong, Zhun, et al. "Generalizing a person retrieval model hetero-and homogeneously." Proceedings of the European Conference on Computer Vision (ECCV). 2018.[Paper]

  • Zhong, Zhun, et al. "Camera style adaptation for person re-identification." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018.[Paper]

  • Wei, Longhui, et al. "Person transfer gan to bridge domain gap for person re-identification." Proceedings of the IEEE conference on computer vision and pattern recognition. 2018.[Paper]

  • Qian, Xuelin, et al. "Pose-normalized image generation for person re-identification." Proceedings of the European conference on computer vision (ECCV). 2018.[Paper]

  • Deng, Weijian, et al. "Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification." Proceedings of the IEEE conference on computer vision and pattern recognition. 2018.[Paper]

  • Chen, Yanbei, Xiatian Zhu, and Shaogang Gong. "Instance-guided context rendering for cross-domain person re-identification." Proceedings of the IEEE/CVF International Conference on Computer Vision. 2019.[Paper]

Representation learning based

  • Huang, Yangru, et al. "Domain adaptive attention model for unsupervised cross-domain person re-identification." arXiv preprint arXiv:1905.10529 (2019).[Paper]

  • Qi, Lei, et al. A novel unsupervised camera-aware domain adaptation framework for person re-identification." Proceedings of the IEEE/CVF International Conference on Computer Vision. 2019.[Paper]

  • Jin, Xin, et al. "Style normalization and restitution for generalizable person re-identification." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020.[Paper]

  • Zhong, Zhun, et al. "Invariance matters: Exemplar memory for domain adaptive person re-identification." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019.[Paper][Code]

  • Bak, Slawomir, Peter Carr, and Jean-Francois Lalonde. "Domain adaptation through synthesis for unsupervised person re-identification." Proceedings of the European Conference on Computer Vision (ECCV). 2018.[Paper]

  • Lin, Shan, et al. "Multi-task mid-level feature alignment network for unsupervised cross-dataset person re-identification." arXiv preprint arXiv:1807.01440 (2018).[Paper]

  • Wang, Jingya, et al. "Transferable joint attribute-identity deep learning for unsupervised person re-identification." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018.[Paper]

  • Li, Yu-Jhe, et al. "Adaptation and re-identification network: An unsupervised deep transfer learning approach to person re-identification." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 2018.[Paper]

  • Lv, Jianming, et al. "Unsupervised cross-dataset person re-identification by transfer learning of spatial-temporal patterns." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018.[Paper][Code]

  • Geng, Mengyue, et al. "Deep transfer learning for person re-identification." arXiv preprint arXiv:1611.05244 (2016).[Paper]

  • Peng, Peixi, et al. "Unsupervised cross-dataset transfer learning for person re-identification." Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.[Paper]//ļ¼Ÿ

  • Ma, Andy J., et al. "Cross-domain person reidentification using domain adaptation ranking svms." IEEE transactions on image processing 24.5 (2015): 1599-1613.[Paper]

  • Huang, Houjing, et al. "Eanet: Enhancing alignment for cross-domain person re-identification." arXiv preprint arXiv:1812.11369 (2018).[Paper][Code]

  • Zhang, Xinyu, et al. "Self-training with progressive augmentation for unsupervised cross-domain person re-identification." Proceedings of the IEEE/CVF International Conference on Computer Vision. 2019.[Paper]//ļ¼Ÿ

  • Wu, Jinlin, et al. "Unsupervised graph association for person re-identification." Proceedings of the IEEE/CVF International Conference on Computer Vision. 2019.[Paper][Code]

  • Lin, Shan, et al. "Multi-task mid-level feature alignment network for unsupervised cross-dataset person re-identification." arXiv preprint arXiv:1807.01440 (2018).[Paper]

Target domain clustering

  • Yu, Hong-Xing, Ancong Wu, and Wei-Shi Zheng. "Cross-view asymmetric metric learning for unsupervised person re-identification." Proceedings of the IEEE international conference on computer vision. 2017.[Paper]

  • Fan, Hehe, et al. "Unsupervised person re-identification: Clustering and fine-tuning." ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 14.4 (2018): 1-18.[Paper]

  • Fu, Yang, et al. "Self-similarity grouping: A simple unsupervised cross domain adaptation approach for person re-identification." Proceedings of the IEEE/CVF International Conference on Computer Vision. 2019.[Paper]

  • Yunpeng Zhai, Shijian Lu, Qixiang Ye, Xuebo Shan, Jie Chen, Rongrong Ji, and Yonghong Tian. Ad-cluster: Augmented discriminative clustering for domain adaptive person re-identification. In CVPR, 2020. 1, 3, 8 [Paper]

  • Zhao, Fang, et al. "Unsupervised domain adaptation with noise resistible mutual-training for person re-identification." European Conference on Computer Vision. Springer, Cham, 2020.[Paper]

  • Wu, Jinlin, et al. "Clustering and dynamic sampling based unsupervised domain adaptation for person re-identification." 2019 IEEE International Conference on Multimedia and Expo (ICME). IEEE, 2019.[Paper]

  • Yang, Fengxiang, et al. "Asymmetric co-teaching for unsupervised cross-domain person re-identification." Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 34. No. 07. 2020.[Paper]

  • Ge, Yixiao, Dapeng Chen, and Hongsheng Li. "Mutual mean-teaching: Pseudo label refinery for unsupervised domain adaptation on person re-identification." arXiv preprint arXiv:2001.01526 (2020).[Paper]

  • Li, Jianing, and Shiliang Zhang. "Joint Visual and Temporal Consistency for Unsupervised Domain Adaptive Person Re-Identification." European Conference on Computer Vision. Springer, Cham, 2020.[Paper]

  • Zhang, Minying, et al. "Unsupervised Domain Adaptation for Person Re-identification via Heterogeneous Graph Alignment." Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 35. No. 4. 2021.[Paper](AAAI2021)

  • Zheng, Kecheng, et al. "Group-aware label transfer for domain adaptive person re-identification." (CVPR2021)[Paper]

  • Jin, Xin, et al. "Global distance-distributions separation for unsupervised person re-identification." European Conference on Computer Vision. Springer, Cham, 2020.[Paper]

  • Wu, Si. "An Attention-driven Two-stage Clustering Method for Unsupervised Person Re-Identification." (2020).(ECCV2020)[Paper]

Pure re-ID

Handcraft feature

  • Zheng, Liang, et al. "Scalable person re-identification: A benchmark." Proceedings of the IEEE international conference on computer vision. 2015.[Paper]

  • S. Liao, Y. Hu, X. Zhu, and S. Z. Li, "Person reidentiļ¬cation by local maximal occurrence representation and metric learning." in CVPR, 2015, pp. 21972206.[Paper]

  • Ma, Bingpeng, Yu Su, and FrĆ©dĆ©ric Jurie. "Bicov: a novel image representation for person re-identification and face verification." British Machive Vision Conference. 2012.[Paper]

  • G. Lisanti, I. Masi, A. D. Bagdanov, and A. Del Bimbo, "Person reidentiļ¬cation by iterative re-weighted sparse ranking," IEEE Trans. Pattern Anal. Mach. Intell., vol. 37, no. 8, pp. 1629ā€“1642, 2015.[Paper]

  • E. Kodirov, T. Xiang, Z. Fu, and S. Gong, "Person re-identiļ¬cation by unsupervised $\ell _1 $ graph learning," in Proc. Eur. Conf. Comput. Vis., 2016, pp. 178ā€“195.[Paper]

  • Yang, Yang, et al. "Unsupervised learning of multi-level descriptors for person re-identification." Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 31. No. 1. 2017.[Paper]

  • Kodirov, Elyor, Tao Xiang, and Shaogang Gong. "Dictionary learning with iterative laplacian regularisation for unsupervised person re-identification." BMVC. Vol. 3. 2015.[Paper]

  • Farenzena, Michela, et al. "Person re-identification by symmetry-driven accumulation of local features." 2010 IEEE computer society conference on computer vision and pattern recognition. IEEE, 2010.[Paper]

  • Wang, Hanxiao, Shaogang Gong, and Tao Xiang. "Unsupervised learning of generative topic saliency for person re-identification." (2014).[Paper]

  • Zhao, Rui, Wanli Oyang, and Xiaogang Wang. "Person re-identification by saliency learning." IEEE transactions on pattern analysis and machine intelligence 39.2 (2016): 356-370.[Paper]

Clustering-based

  • Wang, Dongkai, and Shiliang Zhang. "Unsupervised person re-identification via multi-label classification." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020.[Paper]

  • Lin, Yutian, et al. "Unsupervised person re-identification via softened similarity learning." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020.[Paper][Code]

  • Lin, Yutian, et al. "A bottom-up clustering approach to unsupervised person re-identification." Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 33. No. 01. 2019.[Paper]

  • Ding, Guodong, et al. "Dispersion based Clustering for Unsupervised Person Re-identification." BMVC. 2019.[Paper]

  • Ye, Mang, et al. "Dynamic label graph matching for unsupervised video re-identification." Proceedings of the IEEE international conference on computer vision. 2017.[Paper]

  • Zeng, Kaiwei, et al. "Hierarchical clustering with hard-batch triplet loss for person re-identification." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020.[Paper]

  • Xuan, Shiyu, and Shiliang Zhang. "Intra-Inter Camera Similarity for Unsupervised Person Re-Identification." arXiv preprint arXiv:2103.11658 (2021).[Paper]

  • Wang, Menglin, et al. "Camera-aware Proxies for Unsupervised Person Re-Identification." arXiv preprint arXiv:2012.10674 (2020).[Paper]

  • Yang, Fengxiang, et al. "Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification." arXiv preprint arXiv:2103.04618 (2021).[Paper]

Tracklet based

  • Wu, Guile, Xiatian Zhu, and Shaogang Gong. "Tracklet self-supervised learning for unsupervised person re-identification." Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 34. No. 07. 2020.[Paper]

  • Li, Minxian, Xiatian Zhu, and Shaogang Gong. "Unsupervised tracklet person re-identification." IEEE transactions on pattern analysis and machine intelligence 42.7 (2019): 1770-1782.[Paper]

  • Li, Minxian, Xiatian Zhu, and Shaogang Gong. "Unsupervised person re-identification by deep learning tracklet association." Proceedings of the European conference on computer vision (ECCV). 2018.[Paper]

  • Ye, Mang, Xiangyuan Lan, and Pong C. Yuen. "Robust anchor embedding for unsupervised video person re-identification in the wild." Proceedings of the European Conference on Computer Vision (ECCV). 2018.[Paper]

  • Ma, Xiaolong, et al. "Person re-identification by unsupervised video matching." Pattern Recognition 65 (2017): 197-210.[Paper]

  • Liu, Zimo, Dong Wang, and Huchuan Lu. "Stepwise metric promotion for unsupervised video person re-identification." Proceedings of the IEEE international conference on computer vision. 2017.[Paper]

  • Xie, Qiaokang, et al. "Progressive Unsupervised Person Re-identification by Tracklet Association with Spatio-Temporal Regularization." IEEE Transactions on Multimedia

Other Unsupervised Learning research in Computer Vision or re-ID related works

  • Fernando, Basura, et al. "Unsupervised visual domain adaptation using subspace alignment." Proceedings of the IEEE international conference on computer vision. 2013.[Paper]

  • Gong, Boqing, et al. "Geodesic flow kernel for unsupervised domain adaptation." 2012 IEEE conference on computer vision and pattern recognition. IEEE, 2012.[Paper]

  • Gopalan, Raghuraman, Ruonan Li, and Rama Chellappa. "Domain adaptation for object recognition: An unsupervised approach." 2011 international conference on computer vision. IEEE, 2011.[Paper]

  • Qiu, Qiang, Jie Ni, and Rama Chellappa. "Dictionary-based domain adaptation methods for the re-identification of faces." Person Re-Identification. Springer, London, 2014. 269-285.[Paper]

  • Zheng, Zhedong, Liang Zheng, and Yi Yang. "Unlabeled samples generated by gan improve the person re-identification baseline in vitro." Proceedings of the IEEE International Conference on Computer Vision. 2017.[Paper]

  • Hoffman, Judy, et al. "Cycada: Cycle-consistent adversarial domain adaptation." International conference on machine learning. PMLR, 2018.[Paper][Code]

  • Dong, Xuanyi, et al. "Style aggregated network for facial landmark detection." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018.[Paper][Code]

  • Zhao, Jian, et al. "3D-Aided Deep Pose-Invariant Face Recognition." IJCAI. Vol. 2. No. 3. 2018.[Paper]

  • Isola, Phillip, et al. "Image-to-image translation with conditional adversarial networks." Proceedings of the IEEE conference on computer vision and pattern recognition. 2017.[Paper][Code]

  • Bousmalis, Konstantinos, et al. "Unsupervised pixel-level domain adaptation with generative adversarial networks." Proceedings of the IEEE conference on computer vision and pattern recognition. 2017.[Paper][Code]

  • Zhang, Richard, Phillip Isola, and Alexei A. Efros. "Split-brain autoencoders: Unsupervised learning by cross-channel prediction." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017.[Paper][Code]

  • Bojanowski, Piotr, and Armand Joulin. "Unsupervised learning by predicting noise." International Conference on Machine Learning. PMLR, 2017.[Paper][Code]

  • Chang, Jianlong, et al. "Deep adaptive image clustering." Proceedings of the IEEE international conference on computer vision. 2017.[Paper][Code]

  • Zhu, Jun-Yan, et al. "Unpaired image-to-image translation using cycle-consistent adversarial networks." Proceedings of the IEEE international conference on computer vision. 2017.[Paper][Code]

  • Sun, Yifan, et al. "Svdnet for pedestrian retrieval." Proceedings of the IEEE International Conference on Computer Vision. 2017.[Paper]

  • Lee, Hsin-Ying, et al. "Unsupervised representation learning by sorting sequences." Proceedings of the IEEE International Conference on Computer Vision. 2017.[Paper][Code]

  • Gatys, Leon A., Alexander S. Ecker, and Matthias Bethge. "Image style transfer using convolutional neural networks." Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.[Paper]

  • Bousmalis, Konstantinos, et al. "Domain separation networks." arXiv preprint arXiv:1608.06019 (2016).[Paper]

  • Taigman, Yaniv, Adam Polyak, and Lior Wolf. "Unsupervised cross-domain image generation." arXiv preprint arXiv:1611.02200 (2016).[Paper][Code]

  • Johnson, Justin, Alexandre Alahi, and Li Fei-Fei. "Perceptual losses for real-time style transfer and super-resolution." European conference on computer vision. Springer, Cham, 2016.[Paper][Code]

  • Sun, Baochen, Jiashi Feng, and Kate Saenko. "Return of frustratingly easy domain adaptation." Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 30. No. 1. 2016.[Paper]

  • Sun, Baochen, and Kate Saenko. "Deep coral: Correlation alignment for deep domain adaptation." European conference on computer vision. Springer, Cham, 2016.[Paper][Code]

  • Radford, Alec, Luke Metz, and Soumith Chintala. "Unsupervised representation learning with deep convolutional generative adversarial networks." arXiv preprint arXiv:1511.06434 (2015).[Paper][Code]

  • Bojanowski, Piotr, et al. "Weakly supervised action labeling in videos under ordering constraints." European Conference on Computer Vision. Springer, Cham, 2014.[Paper]

  • Goodfellow I J, Pouget-Abadie J, Mirza M, et al. "Generative adversarial nets." Proceedings of the 27th International Conference on Neural Information Processing Systems. Cambridge: MIT Press, 2014:2672-2680.

  • Tzeng, Eric, et al. "Deep domain confusion: Maximizing for domain invariance." arXiv preprint arXiv:1412.3474 (2014).[Paper][Code]

  • Fernando, Basura, et al. "Unsupervised visual domain adaptation using subspace alignment." Proceedings of the IEEE international conference on computer vision. 2013.[Paper]

  • Gong, Boqing, et al. "Geodesic flow kernel for unsupervised domain adaptation." 2012 IEEE conference on computer vision and pattern recognition. IEEE, 2012.[Paper]

  • Gong, Boqing, et al. "Geodesic flow kernel for unsupervised domain adaptation." 2012 IEEE conference on computer vision and pattern recognition. IEEE, 2012.[Paper]

  • Ma, Bingpeng, Yu Su, and FrĆ©dĆ©ric Jurie. "Local descriptors encoded by fisher vectors for person re-identification." European conference on computer vision. Springer, Berlin, Heidelberg, 2012.[Paper]

Semi-supervised Learning or Few-shot Learning

  • Li, Jiawei, Andy J. Ma, and Pong C. Yuen. "Semi-supervised region metric learning for person re-identification." International Journal of Computer Vision 126.8 (2018): 855-874.

  • Wu, Yu, et al. "Exploit the unknown gradually: One-shot video-based person re-identification by stepwise learning." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018.[Paper]

  • Su, Chi, et al. "Deep attributes driven multi-camera person re-identification." European conference on computer vision. Springer, Cham, 2016.[Paper]

Experience

Comming soon...

Maintainers

@YiminLiu.

License

MIT Ā© Yimin Liu