Advertisement

Cross-Dataset Person Re-identification Using Similarity Preserved Generative Adversarial Networks

  • Jianming Lv
  • Xintong Wang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11062)

Abstract

Person re-identification (Re-ID) aims to match the image frames which contain the same person in the surveillance videos. Most of the Re-ID algorithms conduct supervised training in some small labeled datasets, so directly deploying these trained models to the real-world large camera networks may lead to a poor performance due to underfitting. The significant difference between the source training dataset and the target testing dataset makes it challenging to incrementally optimize the model. To address this challenge, we propose a novel solution by transforming the unlabeled images in the target domain to fit the original classifier by using our proposed similarity preserved generative adversarial networks model, SimPGAN. Specifically, SimPGAN adopts the generative adversarial networks with the cycle consistency constraint to transform the unlabeled images in the target domain to the style of the source domain. Meanwhile, SimPGAN uses the similarity consistency loss, which is measured by a siamese deep convolutional neural network, to preserve the similarity of the transformed images of the same person. Comprehensive experiments based on multiple real surveillance datasets are conducted, and the results show that our algorithm is better than the state-of-the-art cross-dataset unsupervised person Re-ID algorithms.

Keywords

Cross-dataset Person re-identification Similarity preserved 

References

  1. 1.
    Loy, C.C., Xiang, T., Gong, S.: Multi-camera activity correlation analysis. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, pp. 1988–1995. IEEE (2009)Google Scholar
  2. 2.
    Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672–2680 (2014)Google Scholar
  3. 3.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)Google Scholar
  4. 4.
    van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(Nov), 2579–2605 (2008)MATHGoogle Scholar
  5. 5.
    Isola, P., Jun-Yan, Z., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. arXiv preprint (2017)Google Scholar
  6. 6.
    Layne, R., Hospedales, T.M., Gong, S.: Domain transfer for person re-identification. In: Proceedings of the 4th ACM/IEEE International Workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Stream, pp. 25–32. ACM (2013)Google Scholar
  7. 7.
    Liang, C., Huang, B., Hu, R., Zhang, C., Jing, X., Xiao, J.: A unsupervised person re-identification method using model based representation and ranking. In: Proceedings of the 23rd ACM International Conference on Multimedia, pp. 771–774. ACM (2015)Google Scholar
  8. 8.
    Liao, S., Hu, Y., Zhu, X., Li, S.Z.: Person re-identification by local maximal occurrence representation and metric learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2197–2206 (2015)Google Scholar
  9. 9.
    Ma, L., Yang, X., Tao, D.: Person re-identification over camera networks using multi-task distance metric learning. IEEE Trans. Image Process. 23(8), 3656–3670 (2014)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Ma, A.J., Li, J., Yuen, P.C., Li, P.: Cross-domain person reidentification using domain adaptation ranking svms. IEEE Trans. Image Process. 24(5), 1599–1613 (2015)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Peng, P., et al.: Unsupervised cross-dataset transfer learning for person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1306–1315 (2016)Google Scholar
  12. 12.
    Tao, D., Guo, Y., Song, M., Li, Y., Yu, Z., Tang, Y.Y.: Person re-identification by dual-regularized kiss metric learning. IEEE Trans. Image Process. 25(6), 2726–2738 (2016)MathSciNetCrossRefGoogle Scholar
  13. 13.
    Matsukawa, T., Okabe, T., Suzuki, E., Sato, Y.: Hierarchical Gaussian descriptor for person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1363–1372 (2016)Google Scholar
  14. 14.
    Li, W., Wang, X.: Locally aligned feature transforms across views. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3594–3601. IEEE (2013)Google Scholar
  15. 15.
    Li, W., Zhu, X., Gong, S.: Person re-identification by deep joint learning of multi-loss classification. arXiv preprint arXiv:1705.04724 (2017)
  16. 16.
    Wu, L., Shen, C., van den Hengel, A.: Deep linear discriminant analysis on fisher networks: a hybrid architecture for person re-identification. Pattern Recogn. 65, 238–250 (2017)CrossRefGoogle Scholar
  17. 17.
    Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., Tian, Q.: Scalable person re-identification: a benchmark. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1116–1124 (2015)Google Scholar
  18. 18.
    Zheng, Z., Zheng, L., Yang, Y.: A discriminatively learned CNN embedding for person reidentification. ACM Trans. Multimed. Comput. Commun. Appl. (TOMM) 14(1), 13 (2017)MathSciNetGoogle Scholar
  19. 19.
    Zhu, J.-Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. arXiv preprint arXiv:1703.10593 (2017)

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.South China University of TechnologyGuangzhouChina

Personalised recommendations