Advertisement

Multi-task Network Learning Representation Features of Attributes and Identity for Person Re-identification

  • Junqian Wang
  • Mengsi Lyu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10996)

Abstract

Person re-identification (re-ID) has become increasingly popular due to its significance in practical application. In most of the available methods for person re-ID, the solutions focus on verification and recognition of the person identity and pay main attention to the appearance details of person. In this paper, we propose multi-task network architecture to learn powerful representation features of attributes and identity for person re-ID. Firstly, we utilize the semantic descriptor on attributes such as gender, clothing details to effectively learn representation features. Secondly, we employ joint supervision of softmax loss and center loss for person identification to obtain deep features with inter-class dispersion and intra-class compactness. Finally, we use the convolutional neural network (CNN) and multi-task learning strategy to integrate the person attributes and identity to complete classifications tasks for person re-ID. Experiments are conducted on Market1501 and DukeMTMC-reID to verify the efficiency of our method.

Keywords

Person re-identification Convolutional neural network Multi-task learning Person attributes 

Notes

Acknowledgments

This work is supported in part by Natural Science Foundation of Guangdong Province (Grand no. 2017A030313384) and Guangdong Province high-level personnel of special support program (NO. 2016TX03X164).

References

  1. 1.
    Gheissari, N., Sebastian, T.B., Hartley R.: Person re-identification using spatiotemporal appearance. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1528–1535. IEEE Press, New York (2006)Google Scholar
  2. 2.
    Li, D., Chen, X., Zhang, Z., Huang, K.: Learning deep context-aware features over body and latent parts for person re-identification In: Proceedings of 30th IEEE Conference on Computer Vision and Pattern Recognition, pp. 7398–7407. Institute of Electrical and Electronics Engineers Inc., Honolulu (2017)Google Scholar
  3. 3.
    Zhao, C., Wang, X., Miao, D., Wang, H., Zheng, W., Xu, Y., Zhang, D.: Maximal granularity structure and generalized multi-view discriminant analysis person re-identification. Pattern Recogn. 79, 79–96 (2018)CrossRefGoogle Scholar
  4. 4.
    Zhao, R., Ouyang, W., Wang, X.: Learning mid-level filters for person re-identification. In: Proceedings of 27th IEEE Conference on Computer Vision and Pattern Recognition, pp. 144–151. IEEE Computer Society, Columbus (2014)Google Scholar
  5. 5.
    Liu, C., Gong, S., Loy, C.C., Lin, X.: Person re-identification: what features are important? In: Fusiello, A., Murino, V., Cucchiara, R. (eds.) ECCV 2012. LNCS, vol. 7583, pp. 391–401. Springer, Heidelberg (2012).  https://doi.org/10.1007/978-3-642-33863-2_39CrossRefGoogle Scholar
  6. 6.
    Liao, S., Hu, Y., Zhu, X., Li S.Z.: Person re-identification by local maximal occurrence representation and metric learning. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 2197–2206. IEEE Computer Society, Boston (2015)Google Scholar
  7. 7.
    Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., Tian, Q.: Scalable person re-identifitcation: a benchmark. In: Proceedings of IEEE International Conference on Computer Vision, Santiago (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 Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2197–2206. IEEE Computer Society, Boston (2015)Google Scholar
  9. 9.
    Chen, D., Yuan, Z., Chen, B., Zheng, N.: Similarity learning with spatial constraints for person re-identification. In: Proceedings the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1268–1277. IEEE Computer Society, Las Vegas, (2016)Google Scholar
  10. 10.
    Chu, M., Wu, S., Gu, Y., Xu, Y.: Rich features and precise localization with region proposal network for object detection. In: Zhou, J., et al. (eds.) CCBR 2017. LNCS, vol. 10568, pp. 605–614. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-69923-3_65CrossRefGoogle Scholar
  11. 11.
    Zhong, Z., Zhang, B., Lu, G., Zhao, Y., Xu, Y.: An adaptive background modeling method for foreground segmentation. IEEE Trans. Intell. Transp. Syst. 18(5), 1109–1121 (2017)CrossRefGoogle Scholar
  12. 12.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of 29th IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778. IEEE, Las Vegas (2016)Google Scholar
  13. 13.
    Xiao, T., Li, H., Ouyang, W., Wang, X.: Learning deep feature representations with domain guided dropout for person re-identification. In: Proceedings of 29th IEEE Conference on Computer Vision and Pattern Recognition, pp. 1249–1258. IEEE Computer Society, Las Vegas (2016)Google Scholar
  14. 14.
    Zheng, L., et al.: MARS: a video benchmark for large-scale person re-identification. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 868–884. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46466-4_52CrossRefGoogle Scholar
  15. 15.
    Zheng, L., Yang, Y., Hauptmann, A.G.: Person re-identification: past, present and future. arXiv preprint arXiv:1610.02984 (2016)
  16. 16.
    Su, C., Yang, F., Zhang, S., Tian, Q., Davis, L.S., Gao, W.: Multi-task learning with low rank attribute embedding for person re-identification. In: Proceedings of 2015 IEEE International Conference on Computer Vision, pp. 3739–3747. IEEE Computer Society, Santiago (2015)Google Scholar
  17. 17.
    Varior, R.R., Haloi, M., Wang, G.: Gated siamese convolutional neural network architecture for human re-identification. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 791–808. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46484-8_48CrossRefGoogle Scholar
  18. 18.
    Hermans, A., Beyer, L., Leibe, B.: In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737v4 (2017)
  19. 19.
    Cheng, D., Gong, Y., Zhou, S., Wang, J., Zheng, N.: Person re-identification by multi-channel parts-based CNN with improved triplet loss function. In: Proceedings of 29th IEEE Conference on Computer Vision and Pattern Recognition, pp. 1335–1344. IEEE Computer Society, Las Vegas (2016)Google Scholar
  20. 20.
    Varior, R.R., Shuai, B., Lu, J., Xu, D., Wang, G.: A siamese long short-term memory architecture for human re-identification. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 135–153. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46478-7_9CrossRefGoogle Scholar
  21. 21.
    Xiao, T., Li, S., Wang, B., Lin, L., Wang, X.: End-to-end deep learning for person search. arXiv preprint arXiv:1604.01850 (2016)
  22. 22.
    Zheng, L., Zhang, H., Sun, S., Chandraker, M., Tian, Q.: Person re-identification in the wild. arXiv preprint arXiv:1604.02531 (2016)
  23. 23.
    Layne, R., Hospedales T.M., Gong, S.: Re-id: hunting attributes in the wild. In: Proceedings of 25th British Machine Vision Conference, BMVA, Nottingham (2014)Google Scholar
  24. 24.
    Matsukawa, T., Suzuki, E.: Person re-identification using CNN features learned from combination of attributes. In: Proceedings of 23rd International Conference on Pattern Recognition, pp. 2428–2433. IEEE, Cancun (2017)Google Scholar
  25. 25.
    Lin, Y., Zheng, L., Zheng, Z., Wu, Y., Yang, Y.: Improving person re-identification by attribute and identity learning. arXiv preprint arXiv:1703.07220 (2017)
  26. 26.
    Reid, D.A., Nixon, M.S., Stevenage, S.V.: Soft biometrics; human identification using comparative descriptions. IEEE Trans. Pattern Anal. Mach. Intell. 36(6), 1216–1228 (2014)CrossRefGoogle Scholar
  27. 27.
    Wen, Y., Zhang, K., Li, Z., Qiao, Y.: A discriminative feature learning approach for deep face recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 499–515. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46478-7_31CrossRefGoogle Scholar
  28. 28.
    Caruana, R.: Multitask learning. Mach. Learn. 28(1), 41–75 (1997)MathSciNetCrossRefGoogle Scholar
  29. 29.
    Zhong, Z., Zheng, L., Cao, D., Li, S.: Re-ranking person re-identification with k-reciprocal encoding. In: Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition, pp. 3652–3661. Institute of Electrical and Electronics Engineers Inc., Honolulu (2017)Google Scholar
  30. 30.
    Zheng, Z., Zheng, L., Yang, Y.: Unlabeled samples generated by GAN improve the person Re-identification baseline in vitro. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3774–3782. Institute of Electrical and Electronics Engineers Inc., Venice (2017)Google Scholar
  31. 31.
    Zheng, Z., Zheng, L., Yang, Y.: Pedestrian alignment network for large-scale person re-identification. arXiv preprint arXiv:1707.00408v1 (2017)

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Shenzhen Graduate School, Bio-Computer Research CenterHarbin Institute of TechnologyShenzhenChina

Personalised recommendations