Advertisement

Semantically Selective Augmentation for Deep Compact Person Re-Identification

  • Víctor Ponce-LópezEmail author
  • Tilo Burghardt
  • Sion Hannunna
  • Dima Damen
  • Alessandro Masullo
  • Majid Mirmehdi
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11130)

Abstract

We present a deep person re-identification approach that combines semantically selective, deep data augmentation with clustering-based network compression to generate high performance, light and fast inference networks. In particular, we propose to augment limited training data via sampling from a deep convolutional generative adversarial network (DCGAN), whose discriminator is constrained by a semantic classifier to explicitly control the domain specificity of the generation process. Thereby, we encode information in the classifier network which can be utilized to steer adversarial synthesis, and which fuels our CondenseNet ID-network training. We provide a quantitative and qualitative analysis of the approach and its variants on a number of datasets, obtaining results that outperform the state-of-the-art on the LIMA dataset for long-term monitoring in indoor living spaces.

Keywords

Person re-identification Selective augmentation Face filtering Adversarial synthesis Deep compression 

Notes

Acknowledgements

This work was performed under the SPHERE IRC funded by the UK Engineering and Physical Sciences Research Council (EPSRC), Grant EP/K031910/1.

References

  1. 1.
    Barbosa, I.B., Cristani, M., Caputo, B., Rognhaugen, A., Theoharis, T.: Looking beyond appearances: synthetic training data for deep CNNs in re-identification. Comput. Vis. Image Underst. 167, 50–62 (2018).  https://doi.org/10.1016/j.cviu.2017.12.002CrossRefGoogle Scholar
  2. 2.
    Bondi, E., Pala, P., Seidenari, L., Berretti, S., Del Bimbo, A.: Long term person re-identification from depth cameras using facial and skeleton data. In: Wannous, H., Pala, P., Daoudi, M., Flórez-Revuelta, F. (eds.) UHA3DS 2016. LNCS, vol. 10188, pp. 29–41. Springer, Cham (2018).  https://doi.org/10.1007/978-3-319-91863-1_3CrossRefGoogle Scholar
  3. 3.
    Chen, Y., Zhu, X., Gong, S.: Person re-identification by deep learning multi-scale representations. In: IEEE International Conference on Computer Vision Workshops, pp. 2590–2600 (2017). https://doi.org/10.1109/ICCVW.2017.304
  4. 4.
    Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell. 32(9), 1627–1645 (2010).  https://doi.org/10.1109/TPAMI.2009.167CrossRefGoogle Scholar
  5. 5.
    Filković, I., Kalafatić, Z., Hrkać, T.: Deep metric learning for person re-identification and de-identification. In: 2016 39th International Convention on Information and Communication Technology, Electronics and Microelectronics, pp. 1360–1364 (2016). https://doi.org/10.1109/MIPRO.2016.7522351
  6. 6.
    Goodfellow, I., et al.: Generative Adversarial Nets. In: Advances in Neural Information Processing Systems, vol. 27, pp. 2672–2680. Curran Associates, Inc. (2014)Google Scholar
  7. 7.
    Haghighat, M., Abdel-Mottaleb, M.: Low resolution face recognition in surveillance systems using discriminant correlation analysis. In: 2017 12th IEEE International Conference on Automatic Face Gesture Recognition, pp. 912–917 (2017). https://doi.org/10.1109/FG.2017.130
  8. 8.
    Hasan, M., Babaguchi, N.: Long-term people reidentification using anthropometric signature. In: 2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems, pp. 1–6 (2016). https://doi.org/10.1109/BTAS.2016.7791184
  9. 9.
    Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. CoRR abs/1704.04861 (2017)Google Scholar
  10. 10.
    Huang, G., Liu, S., van der Maaten, L., Weinberger, K.Q.: CondenseNet: an efficient densenet using learned group convolutions. preprint arXiv:1711.09224 (2017)
  11. 11.
    Huang, G., Liu, Z., van der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)Google Scholar
  12. 12.
    Khan, F.M., Brèmond, F.: Multi-shot person re-identification using part appearance mixture. In: 2017 IEEE Winter Conference on Applications of Computer Vision, pp. 605–614 (2017). https://doi.org/10.1109/WACV.2017.73
  13. 13.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. CoRR abs/1412.6980 (2014)Google Scholar
  14. 14.
    Layne, R., et al.: A dataset for persistent multi-target multi-camera tracking in RGB-D. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 1462–1470 (2017). https://doi.org/10.1109/CVPRW.2017.189
  15. 15.
    Liu, X., Ma, X., Wang, J., Wang, H.: M3l: multi-modality mining for metric learning in person re-identification. Pattern Recognit. 76, 650–661 (2018).  https://doi.org/10.1016/j.patcog.2017.09.041CrossRefGoogle Scholar
  16. 16.
    Ma, L., Jia, X., Sun, Q., Schiele, B., Tuytelaars, T., Van Gool, L.: Pose guided person image generation. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol. 30, pp. 406–416. Curran Associates, Inc., New York (2017)Google Scholar
  17. 17.
    McConville, R., Byrne, D., Craddock, I., Piechocki, R., Pope, J., Santos-Rodriguez, R.: Understanding the quality of calibrations for indoor localisation. In: IEEE 4th World Forum on Internet of Things (2018). https://doi.org/10.1109/WF-IoT.2018.8355159
  18. 18.
    Perez, L., Wang, J.: The effectiveness of data augmentation in image classification using deep learning. CoRR abs/1712.04621 (2017)Google Scholar
  19. 19.
    Pham, T.T.T., Le, T.L., Dao, T.K.: Improvement of person tracking accuracy in camera network by fusing WiFi and visual information. Informatica 41, 133–148 (2017)Google Scholar
  20. 20.
    Ponce-López, V., Escalante, H.J., Escalera, S., Baró, X.: Gesture and action recognition by evolved dynamic subgestures. In: Proceedings of the British Machine Vision Conference, pp. 129.1–129.13 (2015). https://dx.doi.org/10.5244/C.29.129
  21. 21.
    Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. In: Proceedings of the International Conference on Learning Representations (2015)Google Scholar
  22. 22.
    Ristani, E., Solera, F., Zou, R., Cucchiara, R., Tomasi, C.: Performance measures and a data set for multi-target, multi-camera tracking. In: Hua, G., Jégou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 17–35. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-48881-3_2CrossRefGoogle Scholar
  23. 23.
    Sadri, F.: Ambient intelligence: a survey. ACM Comput. Surv. 43(4), 36:1–36:66 (2011).  https://doi.org/10.1145/1978802.1978815CrossRefGoogle Scholar
  24. 24.
    Shrivastava, A., Pfister, T., Tuzel, O., Susskind, J., Wang, W., Webb, R.: Learning from simulated and unsupervised images through adversarial training. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 2107–2116 (2017)Google Scholar
  25. 25.
    Simon, T., Joo, H., Matthews, I., Sheikh, Y.: Hand keypoint detection in single images using multiview bootstrapping. In: Proceedings of the Computer Vision and Pattern Recognition Conference (2017)Google Scholar
  26. 26.
    Takemura, N., Makihara, Y., Muramatsu, D., Echigo, T., Yagi, Y.: Multi-view large population gait dataset and its performance evaluation for cross-view gait recognition. IPSJ Trans. Comput. Vis. Appl. 10(1), 4 (2018).  https://doi.org/10.1186/s41074-018-0039-6CrossRefGoogle Scholar
  27. 27.
    Twomey, N., et al.: The SPHERE challenge: activity recognition with multimodal sensor data. preprint arXiv:1603.00797 (2016)
  28. 28.
    Wu, L., Wang, Y., Li, X., Gao, J.: What-and-where to match: deep spatially multiplicative integration networks for person re-identification. Pattern Recognit. 76, 727–738 (2018).  https://doi.org/10.1016/j.patcog.2017.10.004CrossRefGoogle Scholar
  29. 29.
    Yu, S.I., Meng, D., Zuo, W., Hauptmann, A.: The solution path algorithm for identity-aware multi-object tracking. In: The IEEE Conference on Computer Vision and Pattern Recognition (2016). https://doi.org/10.1109/CVPR.2016.420
  30. 30.
    Zhang, X., Zhou, X., Lin, M., Sun, J.: ShuffleNet: an extremely efficient convolutional neural network for mobile devices. CoRR abs/1707.01083 (2017). https://arXiv.org/abs/1707.01083
  31. 31.
    Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., Tian, Q.: Scalable person re-identification: A benchmark. In: 2015 IEEE International Conference on Computer Vision, pp. 1116–1124 (2015). https://doi.org/10.1109/ICCV.2015.133
  32. 32.
    Zheng, L., Yang, Y., Hauptmann, A.G.: Person re-identification: past, present and future. arXiv preprint arXiv:1610.02984 (2016)
  33. 33.
    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. 3754–3762 (2017). https://doi.org/10.1109/ICCV.2017.405
  34. 34.
    Zhou, S., et al.: Deep self-paced learning for person re-identification. Pattern Recognit. 76, 739–751 (2018).  https://doi.org/10.1016/j.patcog.2017.10.005CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Department of Computer Science, Faculty of EngineeringUniversity of BristolBristolUK

Personalised recommendations