Camera-aware Proxies for Unsupervised Person Re-Identification

This paper tackles the purely unsupervised person reidentification (Re-ID) problem that requires no annotations. Some previous methods adopt clustering techniques to generate pseudo labels and use the produced labels to train ReID models progressively. These methods are relatively simple but effective. However, most clustering-based methods take each cluster as a pseudo identity class, neglecting the large intra-ID variance caused mainly by the change of camera views. To address this issue, we propose to split each single cluster into multiple proxies and each proxy represents the instances coming from the same camera. These camera-aware proxies enable us to deal with large intra-ID variance and generate more reliable pseudo labels for learning. Based on the camera-aware proxies, we design both intraand inter-camera contrastive learning components for our Re-ID model to effectively learn the ID discrimination ability within and across cameras. Meanwhile, a proxybalanced sampling strategy is also designed, which facilitates our learning further. Extensive experiments on three largescale Re-ID datasets show that our proposed approach outperforms most unsupervised methods by a significant margin. Especially, on the challenging MSMT17 dataset, we gain 14.3 percent Rank-1 and 10.2 percent mAP improvements when compared to the second place. Code is available at: https://github.com/Terminator8758/CAP-master.

[1]  Chenggang Yan,et al.  Unsupervised Person Re-Identification via Softened Similarity Learning , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[3]  Yinghuan Shi,et al.  Adversarial Camera Alignment Network for Unsupervised Cross-Camera Person Re-Identification , 2019, IEEE Transactions on Circuits and Systems for Video Technology.

[4]  Lucas Beyer,et al.  In Defense of the Triplet Loss for Person Re-Identification , 2017, ArXiv.

[5]  Rongrong Ji,et al.  AD-Cluster: Augmented Discriminative Clustering for Domain Adaptive Person Re-Identification , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[7]  Shengcai Liao,et al.  Unsupervised Graph Association for Person Re-Identification , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[8]  Qi Qian,et al.  SoftTriple Loss: Deep Metric Learning Without Triplet Sampling , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[9]  Yair Movshovitz-Attias,et al.  No Fuss Distance Metric Learning Using Proxies , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[10]  Longhui Wei,et al.  Person Transfer GAN to Bridge Domain Gap for Person Re-identification , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[11]  Yinghuan Shi,et al.  A Novel Unsupervised Camera-Aware Domain Adaptation Framework for Person Re-Identification , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[12]  Zheng-Jun Zha,et al.  Adaptive Transfer Network for Cross-Domain Person Re-Identification , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Yi Yang,et al.  Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in Vitro , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[14]  Zhiming Luo,et al.  Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-Identification , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Qi Tian,et al.  Beyond Part Models: Person Retrieval with Refined Part Pooling , 2017, ECCV.

[16]  Yang Yang,et al.  ABD-Net: Attentive but Diverse Person Re-Identification , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[17]  Yi Yang,et al.  Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[18]  Liang Zheng,et al.  Re-ranking Person Re-identification with k-Reciprocal Encoding , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Jian-Huang Lai,et al.  Unsupervised Person Re-Identification by Camera-Aware Similarity Consistency Learning , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[20]  Qi Tian,et al.  Scalable Person Re-identification: A Benchmark , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[21]  Shaogang Gong,et al.  Deep Association Learning for Unsupervised Video Person Re-identification , 2018, BMVC.

[22]  Shaogang Gong,et al.  Unsupervised Person Re-identification by Deep Learning Tracklet Association , 2018, ECCV.

[23]  Manohar Paluri,et al.  Metric Learning with Adaptive Density Discrimination , 2015, ICLR.

[24]  Yaohua Wang,et al.  Hierarchical Clustering With Hard-Batch Triplet Loss for Person Re-Identification , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Xian-Sheng Hua,et al.  Towards Precise Intra-camera Supervised Person Re-Identification , 2020, IEEE Workshop/Winter Conference on Applications of Computer Vision.

[26]  Hongsheng Li,et al.  Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID , 2020, NeurIPS.

[27]  Geoffrey E. Hinton,et al.  A Simple Framework for Contrastive Learning of Visual Representations , 2020, ICML.

[28]  Dapeng Chen,et al.  Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification , 2020, ICLR.

[29]  Stella X. Yu,et al.  Unsupervised Feature Learning via Non-parametric Instance Discrimination , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[30]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[31]  Pong C. Yuen,et al.  Dynamic Label Graph Matching for Unsupervised Video Re-identification , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[32]  Rong Jin,et al.  Large-Scale Distance Metric Learning with Uncertainty , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[33]  Christopher Ré,et al.  No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems , 2020, NeurIPS.

[34]  Liang Zheng,et al.  CycAs: Self-supervised Cycle Association for Learning Re-identifiable Descriptions , 2020, ECCV.

[35]  Hans-Peter Kriegel,et al.  A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise , 1996, KDD.

[36]  Francesco Solera,et al.  Performance Measures and a Data Set for Multi-target, Multi-camera Tracking , 2016, ECCV Workshops.

[37]  Kaiming He,et al.  Momentum Contrast for Unsupervised Visual Representation Learning , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[38]  Liang Zheng,et al.  Unsupervised Person Re-identification: Clustering and Fine-tuning , 2017 .

[39]  Shaogang Gong,et al.  Intra-Camera Supervised Person Re-Identification , 2020, International Journal of Computer Vision.

[40]  Yi Yang,et al.  A Bottom-Up Clustering Approach to Unsupervised Person Re-Identification , 2019, AAAI.

[41]  Shaogang Gong,et al.  Intra-Camera Supervised Person Re-Identification: A New Benchmark , 2019, 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW).

[42]  Yinghuan Shi,et al.  Progressive Cross-Camera Soft-Label Learning for Semi-Supervised Person Re-Identification , 2019, IEEE Transactions on Circuits and Systems for Video Technology.

[43]  Jianhuang Lai,et al.  Smoothing Adversarial Domain Attack and P-Memory Reconsolidation for Cross-Domain Person Re-Identification , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).