Unsupervised Vehicle Re-identification with Progressive Adaptation

IJCAI, pp. 913-919, 2020.

Cited by: 0|Bibtex|Views136|Links
EI
Keywords:
K-Nearest Neighborsreal world sceneaverage precisionideal performanceunsupervised vehicleMore(11+)
Weibo:
We propose an unsupervised vehicle reID framework, named PAL, which iteratively updates the feature learning model and estimates pseudo labels for unlabeled data for target domain adaptation

Abstract:

Vehicle re-identification (reID) aims at identifying vehicles across different non-overlapping cameras views. The existing methods heavily relied on well-labeled datasets for ideal performance, which inevitably causes fateful drop due to the severe domain bias between the training domain and the real-world scenes; worse still, these app...More

Code:

Data:

0
Introduction
  • Vehicle-related research has attracted a great deal of attention, ranging from vehicle detection, tracking [Tang et al, 2019] to classification [Hu et al, 2017].
  • Most of the existing vehicle reID methods, in particular for deep learning models, usually adopt the supervised approaches [Zhao et al, 2019; Lou et al, 2019; Bai et al, 2018; Wang et al, 2017; Guo et al, 2019] for an ideal performance
  • They suffer from the following limitations.
  • How to incrementally optimize the vehicle reID algorithms utilizing the combination of the abundant unlabeled data and existing well-labeled data is practical but challenging
Highlights
  • Vehicle-related research has attracted a great deal of attention, ranging from vehicle detection, tracking [Tang et al, 2019] to classification [Hu et al, 2017]
  • We propose a novel unsupervised method, named PAL, together with Weighted Label Smoothing (WLS) loss to better exploit the unlabeled data, while adapt the target domain to vehicle reID “progressively”
  • Et al, 2019]; (5) CycleGAN [Zhu et al, 2017]. This is method of style transfer, which is employed for the domain adaptation; (6) Direct Transfer: It directly employed the welltrained reID model by the [Zheng et al, 2018] on source domain to the target domain; 7)Baseline System
  • Since only a few works focused on the unsupervised vehicle reID, PUL is compared with the proposed PAL in this paper
  • We propose an unsupervised vehicle reID framework, named PAL, which iteratively updates the feature learning model and estimates pseudo labels for unlabeled data for target domain adaptation
Methods
  • Et al, 2019]; (5) CycleGAN [Zhu et al, 2017]
  • This is method of style transfer, which is employed for the domain adaptation; (6) Direct Transfer: It directly employed the welltrained reID model by the [Zheng et al, 2018] on source domain to the target domain; 7)Baseline System.
  • Since only a few works focused on the unsupervised vehicle reID, PUL is compared with the proposed PAL in this paper.
Results
  • Compared with “Direct Transfer”, it is obvious that the proposed PAL achieves 22.65% and 12.03% gains in mAP and Rank-1 on VeRi-776
Conclusion
  • The authors propose an unsupervised vehicle reID framework, named PAL, which iteratively updates the feature learning model and estimates pseudo labels for unlabeled data for target domain adaptation.
  • The extensive experiments of the developed algorithm has been carried out over benchmark datasets for Vehicle Re-id.
  • It can be observed from the results that compared with other existing unsupervised methods, PAL could achieve superior performance, and even achieve better performance than some typical supervised models
Summary
  • Introduction:

    Vehicle-related research has attracted a great deal of attention, ranging from vehicle detection, tracking [Tang et al, 2019] to classification [Hu et al, 2017].
  • Most of the existing vehicle reID methods, in particular for deep learning models, usually adopt the supervised approaches [Zhao et al, 2019; Lou et al, 2019; Bai et al, 2018; Wang et al, 2017; Guo et al, 2019] for an ideal performance
  • They suffer from the following limitations.
  • How to incrementally optimize the vehicle reID algorithms utilizing the combination of the abundant unlabeled data and existing well-labeled data is practical but challenging
  • Methods:

    Et al, 2019]; (5) CycleGAN [Zhu et al, 2017]
  • This is method of style transfer, which is employed for the domain adaptation; (6) Direct Transfer: It directly employed the welltrained reID model by the [Zheng et al, 2018] on source domain to the target domain; 7)Baseline System.
  • Since only a few works focused on the unsupervised vehicle reID, PUL is compared with the proposed PAL in this paper.
  • Results:

    Compared with “Direct Transfer”, it is obvious that the proposed PAL achieves 22.65% and 12.03% gains in mAP and Rank-1 on VeRi-776
  • Conclusion:

    The authors propose an unsupervised vehicle reID framework, named PAL, which iteratively updates the feature learning model and estimates pseudo labels for unlabeled data for target domain adaptation.
  • The extensive experiments of the developed algorithm has been carried out over benchmark datasets for Vehicle Re-id.
  • It can be observed from the results that compared with other existing unsupervised methods, PAL could achieve superior performance, and even achieve better performance than some typical supervised models
Tables
  • Table1: Performance of different methods on VeRi-776. The best results are shown in bold face. PAL can achieve best performance
  • Table2: Performance of various methods over different reID methods on VehicleID. It is notable that the best results are shown in bold face. PAL can achieve best performance in most situations. Mixed Diff+CCL can also achieve good performance
  • Table3: The settings for different ablation models
  • Table4: Performance of comparison between CEL and BS on VeRi776
  • Table5: Performance of comparison between CEL and BS on VehicleID(2400)
  • Table6: Performance of comparison between OIMG and BS on VeRi-776
  • Table7: Performance of comparison between OIMG and BS on VehicleID (2400)
Download tables as Excel
Funding
  • This work was supported in part by the National Key Research and Development Program of China under grant 2018YFB0804205, by the National Natural Science Foundation of China Grant 61806035, U1936217, 61370142, 61272368, 61672365, 61732008 and 61725203, China Postdoctoral Science Foundation 3620080307, by the Dalian Science and Technology Innovation Fund 2019J11CY001, by the Fundamental Research Funds for the Central Universities Grant 3132016352, by the Liaoning Revitalization Talents Program, XLYC1908007
Reference
  • [Abadi et al., 2016] Martın Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, et al. Tensorflow: A system for large-scale machine learning. In 12th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 16), pages 265–283, 2016.
    Google ScholarLocate open access versionFindings
  • [Almahairi et al., 2018] Amjad Almahairi, Sai Rajeswar, Alessandro Sordoni, Philip Bachman, and Aaron Courville. Augmented cyclegan: Learning many-tomany mappings from unpaired data. arXiv preprint arXiv:1802.10151, 2018.
    Findings
  • [Bai et al., 2018] Yan Bai, Yihang Lou, Feng Gao, Shiqi Wang, Yuwei Wu, and Ling-Yu Duan. Group-sensitive triplet embedding for vehicle reidentification. IEEE Transactions on Multimedia, 20(9):2385–2399, 2018.
    Google ScholarLocate open access versionFindings
  • [Bashir et al., 2019] Raja Muhammad Saad Bashir, Muhammad Shahzad, and MM Fraz. Vr-proud: Vehicle reidentification using progressive unsupervised deep architecture. Pattern Recognition, 90:52–65, 2019.
    Google ScholarLocate open access versionFindings
  • [Fan et al., 2018] Hehe Fan, Liang Zheng, Chenggang Yan, and Yi Yang. Unsupervised person re-identification: Clustering and fine-tuning. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 14(4):83, 2018.
    Google ScholarLocate open access versionFindings
  • [Guo et al., 2019] Haiyun Guo, Kuan Zhu, Ming Tang, and Jinqiao Wang. Two-level attention network with multigrain ranking loss for vehicle re-identification. IEEE Transactions on Image Processing, 2019.
    Google ScholarLocate open access versionFindings
  • [He et al., 2015] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. arXiv preprint arXiv:1512.03385, 2015.
    Findings
  • [Hu et al., 2017] Qichang Hu, Huibing Wang, Teng Li, and Chunhua Shen. Deep cnns with spatially weighted pooling for fine-grained car recognition. IEEE Transactions on Intelligent Transportation Systems, 18(11):3147–3156, 2017.
    Google ScholarLocate open access versionFindings
  • [Huang et al., 2019] Yan Huang, Jingsong Xu, Qiang Wu, Zhedong Zheng, Zhaoxiang Zhang, and Jian Zhang. Multi-pseudo regularized label for generated data in person re-identification. IEEE Transactions on Image Processing, 28(3):1391–1403, 2019.
    Google ScholarLocate open access versionFindings
  • [Isola et al., 2017] Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, and Alexei A Efros. Image-to-image translation with conditional adversarial networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1125–1134, 2017.
    Google ScholarLocate open access versionFindings
  • [Lin et al., 2019] Wu Lin, Wang Yang, and Shao Ling. Cycle-consistent deep generative hashing for cross-modal retrieval. IEEE transactions on image processing: a publication of the IEEE Signal Processing Society, 28(4):1602, 2019.
    Google ScholarLocate open access versionFindings
  • [Liu et al., 2016a] Hongye Liu, Yonghong Tian, Yaowei Yang, Lu Pang, and Tiejun Huang. Deep relative distance learning: Tell the difference between similar vehicles. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 2167–2175, 2016.
    Google ScholarLocate open access versionFindings
  • [Liu et al., 2016b] Xinchen Liu, Wu Liu, Tao Mei, and Huadong Ma. A deep learning-based approach to progressive vehicle re-identification for urban surveillance. In European Conference on Computer Vision, pages 869–884.
    Google ScholarLocate open access versionFindings
  • [Liu et al., 2018] Xinchen Liu, Wu Liu, Tao Mei, and Huadong Ma. Provid: Progressive and multimodal vehicle reidentification for large-scale urban surveillance. IEEE Transactions on Multimedia, 20(3):645–658, 2018.
    Google ScholarLocate open access versionFindings
  • [Lou et al., 2019] Yihang Lou, Yan Bai, Jun Liu, Shiqi Wang, and Ling-Yu Duan. Embedding adversarial learning for vehicle re-identification. IEEE Transactions on Image Processing, 2019.
    Google ScholarLocate open access versionFindings
  • [Taigman et al., 2016] Yaniv Taigman, Adam Polyak, and Lior Wolf. Unsupervised cross-domain image generation. arXiv preprint arXiv:1611.02200, 2016.
    Findings
  • [Tang et al., 2019] Zheng Tang, Milind Naphade, Ming-Yu Liu, Xiaodong Yang, Stan Birchfield, Shuo Wang, Ratnesh Kumar, David Anastasiu, and Jenq-Neng Hwang. Cityflow: A city-scale benchmark for multi-target multicamera vehicle tracking and re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 8797–8806, 2019.
    Google ScholarLocate open access versionFindings
  • [Wang et al., 2017] Zhongdao Wang, Luming Tang, Xihui Liu, Zhuliang Yao, Shuai Yi, Jing Shao, Junjie Yan, Shengjin Wang, Hongsheng Li, and Xiaogang Wang. Orientation invariant feature embedding and spatial temporal regularization for vehicle re-identification. In Proceedings of the IEEE International Conference on Computer Vision, pages 379–387, 2017.
    Google ScholarLocate open access versionFindings
  • [Yi et al., 2017] Zili Yi, Hao Zhang, Ping Tan, and Minglun Gong. Dualgan: Unsupervised dual learning for imageto-image translation. In Proceedings of the IEEE international conference on computer vision, pages 2849–2857, 2017.
    Google ScholarLocate open access versionFindings
  • [Zhao et al., 2019] Yanzhu Zhao, Chunhua Shen, Huibing Wang, and Shengyong Chen. Structural analysis of attributes for vehicle re-identification and retrieval. IEEE Transactions on Intelligent Transportation Systems, 2019.
    Google ScholarLocate open access versionFindings
  • [Zheng et al., 2018] Zhedong Zheng, Liang Zheng, and Yi Yang. A discriminatively learned cnn embedding for person reidentification. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 14(1):13, 2018.
    Google ScholarLocate open access versionFindings
  • [Zhu et al., 2017] Jun-Yan Zhu, Taesung Park, Phillip Isola, and Alexei A Efros. Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proceedings of the IEEE international conference on computer vision, pages 2223–2232, 2017.
    Google ScholarLocate open access versionFindings
Your rating :
0

 

Tags
Comments