Unsupervised Person Re-Identification Based on Measurement Axis

The main focus of unsupervised person re-identification is the clustering of unlabeled samples in the target domain. However, most existing studies neglected to mine the deep semantic information of the target domain and did not consider a better combination of the source domain and the target domain. In this letter, we not only consider the changes of the target domain within its own domain but also mine the deep semantic information of the images by designing a measurement axis component. Then, the deep semantic information mined by the axis is used as the judgment basis of hard negative samples. Moreover, a new loss function is designed in this work to improve the migration ability of the network. Experimental results on two person re-identification domains show that our technology accuracy outperforms the state of the art by a large margin.

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

[2]  Slawomir Bak,et al.  Domain Adaptation through Synthesis for Unsupervised Person Re-identification , 2018, ECCV.

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

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

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

[6]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

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

[8]  Rui Gao,et al.  Cross-Complementary Local Binary Pattern for Robust Texture Classification , 2019, IEEE Signal Processing Letters.

[9]  Yu Wu,et al.  Progressive Learning for Person Re-Identification With One Example , 2019, IEEE Transactions on Image Processing.

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

[11]  Shijie Yu,et al.  Improved Mutual Mean-Teaching for Unsupervised Domain Adaptive Re-ID , 2020, ArXiv.

[12]  Kai Zhao,et al.  A Multiresolution Gray-Scale and Rotation Invariant Descriptor for Texture Classification , 2018, IEEE Access.

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

[14]  Zhedong Zheng,et al.  CamStyle: A Novel Data Augmentation Method for Person Re-Identification , 2019, IEEE Transactions on Image Processing.

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

[16]  Z. Jane Wang,et al.  Compressed Binary Image Hashes Based on Semisupervised Spectral Embedding , 2013, IEEE Transactions on Information Forensics and Security.

[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]  Yi Yang,et al.  Person Re-identification: Past, Present and Future , 2016, ArXiv.

[19]  Vanshika Gupta,et al.  Robust Discriminative Subspace Learning for Person Reidentification , 2019, IEEE Signal Processing Letters.

[20]  Kim-Hui Yap,et al.  AANet: Attribute Attention Network for Person Re-Identifications , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Yali Li,et al.  Open-World Person Re-Identification With Deep Hash Feature Embedding , 2019, IEEE Signal Processing Letters.

[22]  Yu-Chiang Frank Wang,et al.  Adaptation and Re-identification Network: An Unsupervised Deep Transfer Learning Approach to Person Re-identification , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[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 Lu,et al.  Centralized and Clustered Features for Person Re-Identification , 2019, IEEE Signal Processing Letters.

[25]  Qian Du,et al.  Local Binary Patterns and Extreme Learning Machine for Hyperspectral Imagery Classification , 2015, IEEE Transactions on Geoscience and Remote Sensing.

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

[27]  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).

[28]  Lei Zhang,et al.  AsNet: Asymmetrical Network for Learning Rich Features in Person Re-Identification , 2020, IEEE Signal Processing Letters.

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

[30]  Zheng Wang,et al.  Effective and Efficient: Toward Open-world Instance Re-identification , 2020, ACM Multimedia.

[31]  Kai Zhao,et al.  Real-time moving pedestrian detection using contour features , 2018, Multimedia Tools and Applications.

[32]  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).

[33]  Yue Gao,et al.  Deep Multi-View Enhancement Hashing for Image Retrieval , 2020, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[35]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.