Volume 31 Issue 1
Jan.  2022
Turn off MathJax
Article Contents
FU Lihua, DU Yubin, DING Yu, et al., “Domain Adaptive Learning with Multi-Granularity Features for Unsupervised Person Re-identification,” Chinese Journal of Electronics, vol. 31, no. 1, pp. 116-128, 2022, doi: 10.1049/cje.2020.00.072
Citation: FU Lihua, DU Yubin, DING Yu, et al., “Domain Adaptive Learning with Multi-Granularity Features for Unsupervised Person Re-identification,” Chinese Journal of Electronics, vol. 31, no. 1, pp. 116-128, 2022, doi: 10.1049/cje.2020.00.072

Domain Adaptive Learning with Multi-Granularity Features for Unsupervised Person Re-identification

doi: 10.1049/cje.2020.00.072
More Information
  • Author Bio:

    (corresponding author) received the Ph.D. degree in computer science from Northwestern Polytechnical University in 2005. She is currently an Associate Professor with Beijng University of Technology. Her current research interests include image processing and computer vision. (Email: fulh@bjut.edu.cn)

    received the B.S. degree from Shandong University of Technology in 2018. He is currently pursuing the master’s degree with Beijng University of Technology. His current research interests include image processing and computer vision

    received the B.S. degree from Henan University of Science and Technology in 2016. He is currently pursuing the master’s degree with Beijng University of Technology. His current research interests include image processing and computer vision

    received the Ph.D. degree in computer science from Northeastern University in 2003. She is currently a Professor with Beijng University of Technology. Her current research interests include image processing and computer vision

    received the B.S. degree from Beijng University of Technology in 2019. He is currently pursuing the master’s degree with Beijng University of Technology. His current research interests include image processing and computer vision

    received the B.S. degree from Huzhou University in 2019. He is currently pursuing the master’s degree with Beijng University of Technology. His current research interests include image processing and computer vision

  • Received Date: 2020-03-09
  • Accepted Date: 2020-11-13
  • Available Online: 2021-09-23
  • Publish Date: 2022-01-05
  • Unsupervised person re-identification (Re-ID) aims to improve the model’s scalability and obtain better Re-ID results in the unlabeled data domain. In this paper, we propose an unsupervised person Re-ID method based on multi-granularity feature representation and domain adaptive learning, which can effectively improve the performance of unsupervised person re-identification. The multi-granularity feature extraction module integrates global and local information of different granularity to obtain the multi-granularity person feature representation with rich discriminative information. The source domain classification module learns the labeled source dataset classification and obtains the person’s discriminative knowledge in the source domain. On this basis, the domain adaptive module further considers the difference between the target domain and the source domain to learn adaptively for the model. Experiments on multiple public datasets show that the proposed method can achieve a competitive performance among other state-of-the-art unsupervised Re-ID methods.
  • loading
  • [1]
    X. B. Chang, T. M. Hospedales, and T. Xiang, “Multi-level factorisation net for person re-identification,” in Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Utah, pp.2109–2118, 2018.
    [2]
    D. P. Chen, D. Xu, H. S. Li, et al., “Group consistent similarity learning via deep CRF for person re-identification,” in Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Utah, pp.8649–8658, 2018.
    [3]
    W. Li, X. T. Zhu, and S. G. Gong, “Harmonious attention network for person re-identifcation,” in Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Utah, pp.2285–2294, 2018.
    [4]
    G. S. Wang, Y. F. Yuan, X. Chen, et al., “Learning discriminative features with multiple granularities for person re-identification,” in Proc. of the 26th ACM International Conference on Multimedia, Seoul, pp.274–282, 2018.
    [5]
    K. Elyor, T. Xiang, Z. Y. Fu, et al., “Person re-identification by unsupervised graph learning,” in Proc. of European Conference on Computer Vision, Amsterdam, pp.178–195, 2016.
    [6]
    E. Kodirov, T. Xiang, and S. G. Gong, “Dictionary learning with iterative laplacian regularisation for unsupervised person re-identification,” in Proc. of British Machine Vision Conference, Swansea, Vol.3, pp.777–780, 2015.
    [7]
    M. Farenzena, L. Bazzani, A. Perina, et al., “Person re-identification by symmetry-driven accumulation of local features,” in Proc. of IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, California, pp.2360–2367, 2010.
    [8]
    P. X. Peng, T. Xiang, Yaowei Wang, et al., “Unsupervised cross-dataset transfer learning for person reidentification,” in Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, Nevada, pp.1306–1315, 2016.
    [9]
    L. C. Song, C. Wang, L. Zhang, et al., “Unsupervised domain adaptive re-identification: Theory and practice,” Pattern Recognition, vol.102, pp.107–173, 2020.
    [10]
    S. Lin, H. L. Li, C. T. Li, et al., “Multi-task mid-level feature alignment network for unsupervised cross-dataset person re-identification,” in Proc. of British Machine Vision Conference, Newcastle upon Tyne, arXiv: 1807.01440, 2018.
    [11]
    Z. Zhong, L. Zheng, S. Z. Li, et al., “Generalizing a person retrieval model hetero-and homogeneously,” in Proc. of European Conference on Computer Vision, Munich, pp.172–188, 2018.
    [12]
    L. H. Wei, S. L. Zhang, and W. Gao, “Person transfer GAN to bridge domain gap for person re-identification,” in Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Utah, pp.79–88, 2018.
    [13]
    X. S. Wang, Y. R. Li, and Y. H. Cheng, “Hyperspectral image classification based on unsupervised heterogeneous domain adaptation cyclegan,” Chinese Journal of Electronics, vol.29, no.4, pp.608–614, 2020. doi: 10.1049/cje.2020.05.003
    [14]
    W. J. Deng, L. Zheng, Q. X. Ye, et al., “Image-image domain adaptation with preserved selfsimilarity and domain-dissimilarity for person reidentification,” in Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Utah, pp.994–1003, 2018.
    [15]
    Y. H. Li, F. E. Yang, and Y. C. Liu, “Adaptation and re-identification network: An unsupervised deep transfer learing approach to person re-identification,” in Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Utah, pp.172–178, 2018.
    [16]
    M. M. Kalayeh, E. Basaran, M. Gokmen, et al., “Human semantic parsing for person re-identification,” in Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Utah, pp1062–1071, 2018.
    [17]
    J. M. Lv, W. H. Chen, and Q. Li, “Unsupervised cross-dataset person re-identification by transfer learning of spatio-temporal patterns,” in Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Utah, pp.7948–7956, 2018.
    [18]
    H. X. Yu, A. C. Wu, and W. S. Zheng, “Cross-view asymmetric metric learing for unsupervised person re-identification,” in Proc. of IEEE International Conference on Computer Vision, Venice, pp.994–1002, 2017.
    [19]
    S. L. Wang, Q. Li, H. N. Yuan, et al., “Robust clustering with topological graph partition,” Chinese Journal of Electronics, vol.28, no.1, pp.76–84, 2019. doi: 10.1049/cje.2018.09.005
    [20]
    E. Tzeng, J. Hoffman, K. Saenko, et al., “Adversarial discriminative domain adaptation,” in Proc. of IEEE International Conference on Computer Vision, Venice, pp.994–1003, 2017.
    [21]
    J. Y. Wang, X. T. Zhu, S. G. Gong, et al., “Transferable joint attribute-identity deep learning for unsupervised person reidentification,” in Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Utah, pp.2275–2284, 2018.
    [22]
    P. P. Busto and J. Gall, “Open set domain adaptation,” in Proc. of IEEE International Conference on Computer Vision, Venice, pp.754–763, 2017.
    [23]
    H. X. Yu, W. S. Zheng, and A. C. Wu, “Unsupervised person re-identification by soft multilabel learning,” in Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, California, pp.2148–2157, 2019.
    [24]
    Z. Zhong, L. Zheng, Z. M. Luo, et al., “Invariance matters: Exemplar memory for domain adaptive person re-identification,” in Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, California, pp.598–607, 2019.
    [25]
    W. Li, R. Zhao, T. Xiao, et al., “Deepreid: Deep filter pairing neural network for person re-identifcation,” in Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Columbus, Ohio, pp.152–159, 2014.
    [26]
    Y. Dong, L. Zhen, S. C. Liao, et al., “Deep metric learning for person re-identification,” in Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Columbus, Ohio, pp.34–39, 2014.
    [27]
    L. Zheng, Y. Yang, and A. G. Hauptmann, “Person re-identification: Past, present and future,” arXiv preprint, arXiv: 1610.02984, 2016.
    [28]
    L. Zheng, Y. J. Huang, H. C. Lu, et al., “Pose invariant embedding for deep person reidentification,” arXiv preprint, arXiv: 1701.07732, 2017.
    [29]
    C. Su, J. N. Li, S. L. Zhang, et al., “Pose-driven deep convolutional model for person re-identifcation,” in Proc. of IEEE International Conference on Computer Vision, Venice, pp.3980–3989, 2017.
    [30]
    X. Bai, M. K. Yang, T. T. Huang, et al., “Deep-person: Learning discriminative deep features for person re-identifcation,” arXiv preprint, arXiv: 1711.10658, 2017.
    [31]
    Y. F. Sun, L. Zheng, Y. Yang, et al., “Beyond part models: Person retrieval with refined part pooling,” in Proc. of European Conference on Computer Vision, Munich, pp.480–496, 2018.
    [32]
    Y. J. Choi, M. J. Choi, M. Y. Kim, et al., “Stargan: Unified generative adversarial networks for multi-domain image-toimage translation,” in Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Utah, pp.8789–8797, 2018.
    [33]
    J. Deng, W. Dong, R. Socher, et al., “Imagenet: A large-scale hierarchical image database,” in Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, California, pp.248–255, 2019.
    [34]
    S. C. Liao, Y. Hu, X. Y. Zhu, et al., “Person re-identification by local maximal occurrence representation and metric learning,” in Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Boston, Massachusetts, pp.2197–2206, 2015.
    [35]
    L. Zheng, L. Y. Shen, L. Tian, et al., “Scalable person re-identification: A benchmark,” in Proc. of IEEE International Conference on Computer Vision, Santiago, pp.1116– 1124, 2015.
    [36]
    H. H. Fan, L. Zheng, C. G. Yan, et al., “Unsupervised person re-identification: Clustering and fine-tuning,” ACM Transactions on Multimedia Computing, Communications, and Applications, vol.14, no.4, pp.1–18, 2018.
    [37]
    Z. Zhong, L. Zheng, Z. D. Zheng, et al., “Camstyle: A novel data augmentation method for person re-identification,” IEEE Transactions on Image Processing, vol.28, no.3, pp.1176–1190, 2018.
  • 加载中

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Figures(5)  / Tables(4)

    Article Metrics

    Article views (832) PDF downloads(50) Cited by()
    Proportional views
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return