skip to main content
research-article

Clustering Matters: Sphere Feature for Fully Unsupervised Person Re-identification

Authors Info & Claims
Published:15 March 2022Publication History
Skip Abstract Section

Abstract

In person re-identification (Re-ID), the data annotation cost of supervised learning, is huge and it cannot adapt well to complex situations. Therefore, compared with supervised deep learning methods, unsupervised methods are more in line with actual needs. In unsupervised learning, a key to solving Re-ID is to find a standard that can effectively distinguish the difference (distance) between the features of images belonging to different pedestrian identities. However, there are some differences in the images captured by different cameras (such as brightness, angle, etc.). It is well known that the training of neural networks is mainly based on the distance between features, while in unsupervised learning, especially in unsupervised learning methods based on hierarchical clustering, the distance between features plays a more important role in the clustering phase. We improve the accuracy of a deep learning method based on hierarchical clustering under fully unsupervised conditions, starting from both feature and distance metrics. First, we propose to use spherical features, by normalizing the images in the feature space, to weaken the structural differences (length) between features, while saving the feature differences (direction) between different identities. Then, we use the sum of squared errors (SSE) as a regularization term to balance different cluster states. We evaluate our method on four large-scale Re-ID datasets, and experiments show that our method achieves better results than the state-of-the-art unsupervised methods.

REFERENCES

  1. [1] Ainam Jean-Paul, Qin Ke, Liu Guisong, Luo Guangchun, and Agyemang Brighter. 2020. Enforcing affinity feature learning through self-attention for person re-identification. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 16, 1 (2020), 122.Google ScholarGoogle ScholarDigital LibraryDigital Library
  2. [2] Bai Zechen, Wang Zhigang, Wang Jian, Hu Di, and Ding Errui. 2021. Unsupervised multi-source domain adaptation for person re-identification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 1291412923.Google ScholarGoogle ScholarCross RefCross Ref
  3. [3] Chen Yanbei, Zhu Xiatian, and Gong Shaogang. 2018. Deep association learning for unsupervised video person re-identification. arXiv preprint arXiv:1808.07301 (2018).Google ScholarGoogle Scholar
  4. [4] Cheng De, Gong Yihong, Zhou Sanping, Wang Jinjun, and Zheng Nanning. 2016. Person re-identification by multi-channel parts-basedCNN with improved triplet loss function. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 13351344.Google ScholarGoogle ScholarCross RefCross Ref
  5. [5] Deng Weijian, Zheng Liang, Ye Qixiang, Kang Guoliang, Yang Yi, and Jiao Jianbin. 2018. Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 9941003.Google ScholarGoogle ScholarCross RefCross Ref
  6. [6] Ding Guodong, Khan Salman, Tang Zhenmin, Zhang Jian, and Porikli Fatih. 2019. Towards better validity: Dispersion based clustering for unsupervised person re-identification. arXiv preprint arXiv:1906.01308 (2019).Google ScholarGoogle Scholar
  7. [7] Ding Shengyong, Lin Liang, Wang Guangrun, and Chao Hongyang. 2015. Deep feature learning with relative distance comparison for person re-identification. Pattern Recognition 48, 10 (2015), 29933003.Google ScholarGoogle ScholarDigital LibraryDigital Library
  8. [8] Ding Yuhang, Fan Hehe, Xu Mingliang, and Yang Yi. 2020. Adaptive exploration for unsupervised person re-identification. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 16, 1 (2020), 119.Google ScholarGoogle ScholarDigital LibraryDigital Library
  9. [9] Fan Hehe, Zheng Liang, Yan Chenggang, and Yang Yi. 2018. Unsupervised person re-identification: Clustering and fine-tuning. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 14, 4 (2018), 83.Google ScholarGoogle Scholar
  10. [10] Fan Xing, Jiang Wei, Luo Hao, and Fei Mengjuan. 2019. SphereReID: Deep hypersphere manifold embedding for person re-identification. Journal of Visual Communication and Image Representation 60 (2019), 5158.Google ScholarGoogle ScholarDigital LibraryDigital Library
  11. [11] Grigorev Aleksei, Liu Shaohui, Tian Zhihong, Xiong Jianxin, Rho Seungmin, and Feng Jiang. 2020. Delving deeper in drone-based person Re-Id by employing deep decision forest and attributes fusion. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 16, 1s (2020), 115.Google ScholarGoogle ScholarDigital LibraryDigital Library
  12. [12] Li Wei, Zhao Rui, Xiao Tong, and Wang Xiaogang. 2014. DeepReID: Deep filter pairing neural network for person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 152159.Google ScholarGoogle ScholarDigital LibraryDigital Library
  13. [13] Li Yaoyu, Yao Hantao, Zhang Tianzhu, and Xu Changsheng. 2020. Part-based structured representation learning for person re-identification. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 16, 4 (2020), 122.Google ScholarGoogle ScholarDigital LibraryDigital Library
  14. [14] Li Zhaoju, Zhou Zongwei, Jiang Nan, Han Zhenjun, Xing Junliang, and Jiao Jianbin. 2020. Spatial preserved graph convolution networks for person re-identification. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 16, 1s (2020), 114.Google ScholarGoogle ScholarDigital LibraryDigital Library
  15. [15] Lin Yutian, Dong Xuanyi, Zheng Liang, Yan Yan, and Yang Yi. 2019. A bottom-up clustering approach to unsupervised person re-identification. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33. 87388745.Google ScholarGoogle ScholarDigital LibraryDigital Library
  16. [16] Lin Yutian, Xie Lingxi, Wu Yu, Yan Chenggang, and Tian Qi. 2020. Unsupervised person re-identification via softened similarity learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 33903399.Google ScholarGoogle ScholarCross RefCross Ref
  17. [17] Liu Hao, Feng Jiashi, Qi Meibin, Jiang Jianguo, and Yan Shuicheng. 2017. End-to-end comparative attention networks for person re-identification. IEEE Transactions on Image Processing 26, 7 (2017), 34923506.Google ScholarGoogle ScholarDigital LibraryDigital Library
  18. [18] Liu Weiyang, Wen Yandong, Yu Zhiding, Li Ming, Raj Bhiksha, and Song Le. 2017. Sphereface: Deep hypersphere embedding for face recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 212220.Google ScholarGoogle ScholarCross RefCross Ref
  19. [19] Luo Chuanchen, Song Chunfeng, and Zhang Zhaoxiang. 2020. Generalizing person re-identification by camera-aware invariance learning and cross-domain mixup. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XV 16. Springer, 224241.Google ScholarGoogle ScholarDigital LibraryDigital Library
  20. [20] Maaten Laurens van der and Hinton Geoffrey. 2008. Visualizing data using t-SNE. Journal of Machine Learning Research 9, Nov (2008), 25792605.Google ScholarGoogle Scholar
  21. [21] Miao Jiaxu, Wu Yu, Liu Ping, Ding Yuhang, and Yang Yi. 2019. Pose-guided feature alignment for occluded person re-identification. In Proceedings of the IEEE International Conference on Computer Vision. 542551.Google ScholarGoogle ScholarCross RefCross Ref
  22. [22] Qi Lei, Wang Lei, Huo Jing, Shi Yinghuan, and Gao Yang. 2021. GreyReID: A novel two-stream deep framework with RGB-grey information for person re-identification. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 17, 1 (2021), 122.Google ScholarGoogle ScholarDigital LibraryDigital Library
  23. [23] Qian Xuelin, Fu Yanwei, Xiang Tao, Wang Wenxuan, Qiu Jie, Wu Yang, Jiang Yu-Gang, and Xue Xiangyang. 2018. Pose-normalized image generation for person re-identification. In Proceedings of the European Conference on Computer Vision (ECCV). 650667.Google ScholarGoogle ScholarCross RefCross Ref
  24. [24] Quan Ruijie, Dong Xuanyi, Wu Yu, Zhu Linchao, and Yang Yi. 2019. Auto-ReID: Searching for a part-aware ConvNet for person re-identification. In Proceedings of the IEEE International Conference on Computer Vision. 37503759.Google ScholarGoogle ScholarCross RefCross Ref
  25. [25] Ristani Ergys, Solera Francesco, Zou Roger, Cucchiara Rita, and Tomasi Carlo. 2016. Performance measures and a data set for multi-target, multi-camera tracking. In European Conference on Computer Vision Workshop on Benchmarking Multi-Target Tracking.Google ScholarGoogle ScholarCross RefCross Ref
  26. [26] Ristani Ergys, Solera Francesco, Zou Roger, Cucchiara Rita, and Tomasi Carlo. 2016. Performance measures and a data set for multi-target, multi-camera tracking. In European Conference on Computer Vision. Springer, 1735.Google ScholarGoogle ScholarCross RefCross Ref
  27. [27] Ruan Weijian, Liang Chao, Yu Yi, Wang Zheng, Liu Wu, Chen Jun, and Ma Jiayi. 2020. Correlation discrepancy insight network for video re-identification. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 16, 4 (2020), 121.Google ScholarGoogle ScholarDigital LibraryDigital Library
  28. [28] Shi Hailin, Yang Yang, Zhu Xiangyu, Liao Shengcai, Lei Zhen, Zheng Weishi, and Li Stan Z.. 2016. Embedding deep metric for person re-identification: A study against large variations. In European Conference on Computer Vision. Springer, 732748.Google ScholarGoogle ScholarCross RefCross Ref
  29. [29] Song Jingkuan, Guo Yuyu, Gao Lianli, Li Xuelong, Hanjalic Alan, and Shen Heng Tao. 2018. From deterministic to generative: Multimodal stochastic RNNs for video captioning. IEEE Transactions on Neural Networks and Learning Systems 30, 10 (2018), 30473058.Google ScholarGoogle ScholarCross RefCross Ref
  30. [30] Song Jingkuan, Zhang Hanwang, Li Xiangpeng, Gao Lianli, Wang Meng, and Hong Richang. 2018. Self-supervised video hashing with hierarchical binary auto-encoder. IEEE Transactions on Image Processing 27, 7 (2018), 32103221.Google ScholarGoogle ScholarCross RefCross Ref
  31. [31] Su Chi, Li Jianing, Zhang Shiliang, Xing Junliang, Gao Wen, and Tian Qi. 2017. Pose-driven deep convolutional model for person re-identification. In Proceedings of the IEEE International Conference on Computer Vision. 39603969.Google ScholarGoogle ScholarCross RefCross Ref
  32. [32] Sun Xiaoxiao and Zheng Liang. 2019. Dissecting person re-identification from the viewpoint of viewpoint. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 608617.Google ScholarGoogle ScholarCross RefCross Ref
  33. [33] Sun Yifan, Zheng Liang, Yang Yi, Tian Qi, and Wang Shengjin. 2018. Beyond part models: Person retrieval with refined part pooling (and a strong convolutional baseline). In Proceedings of the European Conference on Computer Vision (ECCV). 480496.Google ScholarGoogle ScholarCross RefCross Ref
  34. [34] Tian Maoqing, Yi Shuai, Li Hongsheng, Li Shihua, Zhang Xuesen, Shi Jianping, Yan Junjie, and Wang Xiaogang. 2018. Eliminating background-bias for robust person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 57945803.Google ScholarGoogle ScholarCross RefCross Ref
  35. [35] Varior Rahul Rama, Haloi Mrinal, and Wang Gang. 2016. Gated siamese convolutional neural network architecture for human re-identification. In European Conference on Computer Vision. Springer, 791808.Google ScholarGoogle ScholarCross RefCross Ref
  36. [36] Varior Rahul Rama, Shuai Bing, Lu Jiwen, Xu Dong, and Wang Gang. 2016. A siamese long short-term memory architecture for human re-identification. In European Conference on Computer Vision. Springer, 135153.Google ScholarGoogle ScholarCross RefCross Ref
  37. [37] Wang Dongkai and Zhang Shiliang. 2020. Unsupervised person re-identification via multi-label classification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 1098110990.Google ScholarGoogle ScholarDigital LibraryDigital Library
  38. [38] Wang Guanshuo, Yuan Yufeng, Chen Xiong, Li Jiwei, and Zhou Xi. 2018. Learning discriminative features with multiple granularities for person re-identification. In 2018 ACM Multimedia Conference on Multimedia Conference. ACM, 274282.Google ScholarGoogle ScholarDigital LibraryDigital Library
  39. [39] Wang Jin, Wang Zheng, Liang Chao, Gao Changxin, and Sang Nong. 2018. Equidistance constrained metric learning for person re-identification. Pattern Recognition 74 (2018), 3851.Google ScholarGoogle ScholarDigital LibraryDigital Library
  40. [40] Wang Jingya, Zhu Xiatian, Gong Shaogang, and Li Wei. 2018. Transferable joint attribute-identity deep learning for unsupervised person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 22752284.Google ScholarGoogle ScholarCross RefCross Ref
  41. [41] Wei Longhui, Zhang Shiliang, Gao Wen, and Tian Qi. 2018. Person transfer GAN to bridge domain gap for person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 7988.Google ScholarGoogle ScholarCross RefCross Ref
  42. [42] Wu Yu, Lin Yutian, Dong Xuanyi, Yan Yan, Bian Wei, and Yang Yi. 2019. Progressive learning for person re-identification with one example. IEEE Transactions on Image Processing 28, 6 (2019), 28722881.Google ScholarGoogle ScholarCross RefCross Ref
  43. [43] Wu Yu, Lin Yutian, Dong Xuanyi, Yan Yan, Ouyang Wanli, and Yang Yi. 2018. Exploit the unknown gradually: One-shot video-based person re-identification by stepwise learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 51775186.Google ScholarGoogle ScholarCross RefCross Ref
  44. [44] Xiao Tong, Li Shuang, Wang Bochao, Lin Liang, and Wang Xiaogang. 2017. Joint detection and identification feature learning for person search. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 34153424.Google ScholarGoogle ScholarCross RefCross Ref
  45. [45] Xie Junyuan, Girshick Ross, and Farhadi Ali. 2016. Unsupervised deep embedding for clustering analysis. In International Conference on Machine Learning. 478487.Google ScholarGoogle ScholarDigital LibraryDigital Library
  46. [46] Xing Eric P., Jordan Michael I., Russell Stuart J., and Ng Andrew Y.. 2003. Distance metric learning with application to clustering with side-information. In Advances in Neural Information Processing Systems. 521528.Google ScholarGoogle ScholarDigital LibraryDigital Library
  47. [47] Yang Qize, Yu Hong-Xing, Wu Ancong, and Zheng Wei-Shi. 2019. Patch-based discriminative feature learning for unsupervised person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 36333642.Google ScholarGoogle ScholarCross RefCross Ref
  48. [48] Ye Mang, Lan Xiangyuan, and Yuen Pong C.. 2018. Robust anchor embedding for unsupervised video person re-identification in the wild. In Proceedings of the European Conference on Computer Vision (ECCV). 170186.Google ScholarGoogle ScholarCross RefCross Ref
  49. [49] Ye Mang, Li Jiawei, Ma Andy J., Zheng Liang, and Yuen Pong C.. 2019. Dynamic graph co-matching for unsupervised video-based person re-identification. IEEE Transactions on Image Processing 28, 6 (2019), 29762990.Google ScholarGoogle ScholarCross RefCross Ref
  50. [50] Yi Dong, Lei Zhen, Liao Shengcai, and Li Stan Z.. 2014. Deep metric learning for person re-identification. In 2014 22nd International Conference on Pattern Recognition. IEEE, 3439.Google ScholarGoogle ScholarDigital LibraryDigital Library
  51. [51] Yu Hong-Xing, Wu Ancong, and Zheng Wei-Shi. 2017. Cross-view asymmetric metric learning for unsupervised person re-identification. In Proceedings of the IEEE International Conference on Computer Vision. 9941002.Google ScholarGoogle ScholarCross RefCross Ref
  52. [52] Yu Hong-Xing, Zheng Wei-Shi, Wu Ancong, Guo Xiaowei, Gong Shaogang, and Lai Jian-Huang. 2019. Unsupervised person re-identification by soft multilabel learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 21482157.Google ScholarGoogle ScholarCross RefCross Ref
  53. [53] Yu Tianyuan, Li Da, Yang Yongxin, Hospedales Timothy M., and Xiang Tao. 2019. Robust person re-identification by modelling feature uncertainty. In Proceedings of the IEEE International Conference on Computer Vision. 552561.Google ScholarGoogle ScholarCross RefCross Ref
  54. [54] Zeng Kaiwei, Ning Munan, Wang Yaohua, and Guo Yang. 2020. Hierarchical clustering with hard-batch triplet loss for person re-identification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 1365713665.Google ScholarGoogle ScholarCross RefCross Ref
  55. [55] Zhang Anguo, Gao Yueming, Niu Yuzhen, Liu Wenxi, and Zhou Yongcheng. 2021. Coarse-to-fine person re-identification with auxiliary-domain classification and second-order information bottleneck. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 598607.Google ScholarGoogle ScholarCross RefCross Ref
  56. [56] Zhang Xuan, Luo Hao, Fan Xing, Xiang Weilai, Sun Yixiao, Xiao Qiqi, Jiang Wei, Zhang Chi, and Sun Jian. 2017. AlignedReID: Surpassing human-level performance in person re-identification. arXiv preprint arXiv:1711.08184.Google ScholarGoogle Scholar
  57. [57] Zheng Liang, Bie Zhi, Sun Yifan, Wang Jingdong, Su Chi, Wang Shengjin, and Tian Qi. 2016. MARS: A video benchmark for large-scale person re-identification. In European Conference on Computer Vision. Springer, 868884.Google ScholarGoogle ScholarCross RefCross Ref
  58. [58] Zheng Liang, Shen Liyue, Tian Lu, Wang Shengjin, Wang Jingdong, and Tian Qi. 2015. Scalable person re-identification: A benchmark. In Proceedings of the IEEE International Conference on Computer Vision. 11161124.Google ScholarGoogle ScholarDigital LibraryDigital Library
  59. [59] Zheng Liang, Zhang Hengheng, Sun Shaoyan, Chandraker Manmohan, Yang Yi, and Tian Qi. 2017. Person re-identification in the wild. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 13671376.Google ScholarGoogle ScholarCross RefCross Ref
  60. [60] Zheng Yi, Zhou Yong, Zhao Jiaqi, Jian Meng, Yao Rui, Liu Bing, and Liu Xuning. 2019. A siamese pedestrian alignment network for person re-identification. In Chinese Conference on Pattern Recognition and Computer Vision (PRCV). Springer, 409420.Google ScholarGoogle ScholarDigital LibraryDigital Library
  61. [61] Zheng Zhedong, Yang Xiaodong, Yu Zhiding, Zheng Liang, Yang Yi, and Kautz Jan. 2019. Joint discriminative and generative learning for person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 21382147.Google ScholarGoogle ScholarCross RefCross Ref
  62. [62] Zheng Zhedong, Zheng Liang, and Yang Yi. 2017. A discriminatively learned CNN embedding for person reidentification. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 14, 1 (2017), 120.Google ScholarGoogle ScholarDigital LibraryDigital Library
  63. [63] Zheng Zhedong, Zheng Liang, and Yang Yi. 2017. Unlabeled samples generated by GAN improve the person re-identification baseline in vitro. In Proceedings of the IEEE International Conference on Computer Vision. 37543762.Google ScholarGoogle ScholarCross RefCross Ref
  64. [64] Zheng Zhedong, Zheng Liang, and Yang Yi. 2018. Pedestrian alignment network for large-scale person re-identification. IEEE Transactions on Circuits and Systems for Video Technology.Google ScholarGoogle Scholar
  65. [65] Zhong Zhun, Zheng Liang, Kang Guoliang, Li Shaozi, and Yang Yi. 2020. Random erasing data augmentation. In AAAI. 1300113008.Google ScholarGoogle Scholar
  66. [66] Zhong Zhun, Zheng Liang, Luo Zhiming, Li Shaozi, and Yang Yi. 2019. Invariance matters: Exemplar memory for domain adaptive person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 598607.Google ScholarGoogle ScholarCross RefCross Ref
  67. [67] Zhong Zhun, Zheng Liang, Zheng Zhedong, Li Shaozi, and Yang Yi. 2018. CamStyle: A novel data augmentation method for person re-identification. IEEE Transactions on Image Processing 28, 3 (2018), 11761190.Google ScholarGoogle ScholarDigital LibraryDigital Library

Index Terms

  1. Clustering Matters: Sphere Feature for Fully Unsupervised Person Re-identification

                Recommendations

                Comments

                Login options

                Check if you have access through your login credentials or your institution to get full access on this article.

                Sign in

                Full Access

                • Published in

                  cover image ACM Transactions on Multimedia Computing, Communications, and Applications
                  ACM Transactions on Multimedia Computing, Communications, and Applications  Volume 18, Issue 4
                  November 2022
                  497 pages
                  ISSN:1551-6857
                  EISSN:1551-6865
                  DOI:10.1145/3514185
                  • Editor:
                  • Abdulmotaleb El Saddik
                  Issue’s Table of Contents

                  Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

                  Publisher

                  Association for Computing Machinery

                  New York, NY, United States

                  Publication History

                  • Published: 15 March 2022
                  • Revised: 1 November 2021
                  • Accepted: 1 November 2021
                  • Received: 1 March 2021
                  Published in tomm Volume 18, Issue 4

                  Permissions

                  Request permissions about this article.

                  Request Permissions

                  Check for updates

                  Qualifiers

                  • research-article
                  • Refereed

                PDF Format

                View or Download as a PDF file.

                PDF

                eReader

                View online with eReader.

                eReader

                Full Text

                View this article in Full Text.

                View Full Text

                HTML Format

                View this article in HTML Format .

                View HTML Format
                About Cookies On This Site

                We use cookies to ensure that we give you the best experience on our website.

                Learn more

                Got it!