Intra-Inter Camera Similarity for Unsupervised Person Re-Identification

Most of unsupervised person Re-Identification (Re-ID) works produce pseudo-labels by measuring the feature similarity without considering the distribution discrepancy among cameras, leading to degraded accuracy in label computation across cameras. This paper targets to address this challenge by studying a novel intra-inter camera similarity for pseudo-label generation. We decompose the sample similarity computation into two stage, i.e., the intra-camera and inter-camera computations, respectively. The intra-camera computation directly leverages the CNN features for similarity computation within each camera. Pseudo-labels generated on different cameras train the re-id model in a multi-branch network. The second stage considers the classification scores of each sample on different cameras as a new feature vector. This new feature effectively alleviates the distribution discrepancy among cameras and generates more reliable pseudo-labels. We hence train our re-id model in two stages with intra-camera and inter-camera pseudo-labels, respectively. This simple intra-inter camera similarity produces surprisingly good performance on multiple datasets, e.g., achieves rank-1 accuracy of 89.5% on the Market1501 dataset, outperforming the recent unsupervised works by 9+%, and is comparable with the latest transfer learning works that leverage extra annotations.

[1]  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).

[2]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[3]  Shengcai Liao,et al.  Person re-identification by Local Maximal Occurrence representation and metric learning , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[5]  Huchuan Lu,et al.  Deep Mutual Learning , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[6]  Yi Yang,et al.  Camera Style Adaptation for Person Re-identification , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[7]  Jianing Li,et al.  Joint Visual and Temporal Consistency for Unsupervised Domain Adaptive Person Re-Identification , 2020, ECCV.

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

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

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

[11]  Trevor Darrell,et al.  Simultaneous Deep Transfer Across Domains and Tasks , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[12]  Zaïd Harchaoui,et al.  A Fast, Consistent Kernel Two-Sample Test , 2009, NIPS.

[13]  Bohyung Han,et al.  Domain-Specific Batch Normalization for Unsupervised Domain Adaptation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Daniel C. Castro,et al.  Domain Generalization via Model-Agnostic Learning of Semantic Features , 2019, NeurIPS.

[15]  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).

[16]  Xiaoou Tang,et al.  Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net , 2018, ECCV.

[17]  Kate Saenko,et al.  Deep CORAL: Correlation Alignment for Deep Domain Adaptation , 2016, ECCV Workshops.

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

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

[20]  Yi Yang,et al.  Generalizing a Person Retrieval Model Hetero- and Homogeneously , 2018, ECCV.

[21]  Xiaobin Liu,et al.  Domain Adaptive Person Re-Identification via Coupling Optimization , 2020, ACM Multimedia.

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

[23]  Wei Li,et al.  Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-identification , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[24]  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).

[25]  Wei Jiang,et al.  A Strong Baseline and Batch Normalization Neck for Deep Person Re-Identification , 2019, IEEE Transactions on Multimedia.

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

[27]  Yunchao Wei,et al.  Self-Similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-Identification , 2018, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[28]  Harshad Rai,et al.  Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks , 2018 .

[29]  Jian-Huang Lai,et al.  Supplementary Material for “Unsupervised Person Re-identification by Soft Multilabel Learning” , 2019 .

[30]  Longhui Wei,et al.  VP-ReID: Vehicle and Person Re-Identification System , 2018, ICMR.

[31]  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.

[32]  Cuiling Lan,et al.  Global Distance-distributions Separation for Unsupervised Person Re-identification , 2020, ECCV.

[33]  Chang-Tsun Li,et al.  Multi-task Mid-level Feature Alignment Network for Unsupervised Cross-Dataset Person Re-Identification , 2018, BMVC.

[34]  Yang Zou,et al.  Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification , 2020, ECCV.

[35]  Ming Yang,et al.  Self-Guided Hash Coding for Large-Scale Person Re-identification , 2019, 2019 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR).

[36]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[37]  Chunhua Shen,et al.  Self-Training With Progressive Augmentation for Unsupervised Cross-Domain Person Re-Identification , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[38]  Longhui Wei,et al.  Rethinking the Distribution Gap of Person Re-identification with Camera-Based Batch Normalization , 2020, ECCV.

[39]  Rongrong Ji,et al.  Multiple Expert Brainstorming for Domain Adaptive Person Re-identification , 2020, ECCV.

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

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

[42]  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.

[43]  Andrea Vedaldi,et al.  Improved Texture Networks: Maximizing Quality and Diversity in Feed-Forward Stylization and Texture Synthesis , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[44]  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).

[45]  Jian Sun,et al.  AlignedReID: Surpassing Human-Level Performance in Person Re-Identification , 2017, ArXiv.