Advertisement

Adversarial Self-supervised Learning for Semi-supervised 3D Action Recognition

Conference paper
  • 850 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12352)

Abstract

We consider the problem of semi-supervised 3D action recognition which has been rarely explored before. Its major challenge lies in how to effectively learn motion representations from unlabeled data. Self-supervised learning (SSL) has been proved very effective at learning representations from unlabeled data in the image domain. However, few effective self-supervised approaches exist for 3D action recognition, and directly applying SSL for semi-supervised learning suffers from misalignment of representations learned from SSL and supervised learning tasks. To address these issues, we present Adversarial Self-Supervised Learning (ASSL), a novel framework that tightly couples SSL and the semi-supervised scheme via neighbor relation exploration and adversarial learning. Specifically, we design an effective SSL scheme to improve the discrimination capability of learned representations for 3D action recognition, through exploring the data relations within a neighborhood. We further propose an adversarial regularization to align the feature distributions of labeled and unlabeled samples. To demonstrate effectiveness of the proposed ASSL in semi-supervised 3D action recognition, we conduct extensive experiments on NTU and N-UCLA datasets. The results confirm its advantageous performance over state-of-the-art semi-supervised methods in the few label regime for 3D action recognition.

Keywords

Semi-supervised 3D action recognition Self-supervised learning Neighborhood consistency Adversarial learning 

Notes

Acknowledgements

This work is jointly supported by National Key Research and Development Program of China (2016YFB1001000), National Natural Science Foundation of China (61420106015, 61976214, 61721004), Shandong Provincial Key Research and Development Program (Major Scientific and Technological Innovation Project) (NO. 2019JZZY010119). Jiashi Feng was partially supported by MOE Tier 2 MOE2017-T2-2-151, NUS_ECRA_FY17_P08, AISG-100E-2019-035. Chenyang Si was partially supported by the program of China Scholarships Council (No. 201904910608). We thank Jianfeng Zhang for his helpful comments.

References

  1. 1.
    Büchler, U., Brattoli, B., Ommer, B.: Improving spatiotemporal self-supervision by deep reinforcement learning. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11219, pp. 797–814. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01267-0_47CrossRefGoogle Scholar
  2. 2.
    Cao, Z., Simon, T., Wei, S.E., Sheikh, Y.: Realtime multi-person 2D pose estimation using part affinity fields. In: CVPR (2017)Google Scholar
  3. 3.
    Chapelle, O., Scholkopf, B., Zien, A.: Semi-supervised Learning. MIT Press, Cambridge (2006)CrossRefGoogle Scholar
  4. 4.
    Cover, T., Hart, P.: Nearest neighbor pattern classification. IEEE Trans. Inf. Theor. 13, 21–27 (1967)CrossRefGoogle Scholar
  5. 5.
    Dosovitskiy, A., Springenberg, J.T., Riedmiller, M., Brox, T.: Discriminative unsupervised feature learning with convolutional neural networks. In: NIPS (2014)Google Scholar
  6. 6.
    Du, Y., Fu, Y., Wang, L.: Skeleton based action recognition with convolutional neural network. In: ACPR (2015)Google Scholar
  7. 7.
    Du, Y., Wang, W., Wang, L.: Hierarchical recurrent neural network for skeleton based action recognition. In: CVPR (2015)Google Scholar
  8. 8.
    Fernando, B., Bilen, H., Gavves, E., Gould, S.: Self-supervised video representation learning with odd-one-out networks. In: CVPR (2017)Google Scholar
  9. 9.
    Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: ICML (2015)Google Scholar
  10. 10.
    Grandvalet, Y., Bengio, Y.: Semi-supervised learning by entropy minimization. In: NIPS (2005)Google Scholar
  11. 11.
    Hussein, M.E., Torki, M., Gowayyed, M.A., El-Saban, M.: Human action recognition using a temporal hierarchy of covariance descriptors on 3D joint locations. In: IJCAI (2013)Google Scholar
  12. 12.
    Ke, Q., Bennamoun, M., An, S., Sohel, F., Boussaid, F.: A new representation of skeleton sequences for 3D action recognition. In: CVPR (2017)Google Scholar
  13. 13.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)Google Scholar
  14. 14.
    Kingma, D.P., Mohamed, S., Rezende, D.J., Welling, M.: Semi-supervised learning with deep generative models. In: NIPS (2014)Google Scholar
  15. 15.
    Laine, S., Aila, T.: Temporal ensembling for semi-supervised learning. In: ICLR (2017)Google Scholar
  16. 16.
    Lee, D.H.: Pseudo-label: the simple and efficient semi-supervised learning method for deep neural networks. In: ICML (2013)Google Scholar
  17. 17.
    Lee, H.Y., Huang, J.B., Singh, M., Yang, M.H.: Unsupervised representation learning by sorting sequences. In: ICCV (2017)Google Scholar
  18. 18.
    Li, C., Zhong, Q., Xie, D., Pu, S.: Co-occurrence feature learning from skeleton data for action recognition and detection with hierarchical aggregation. In: IJCAI (2018)Google Scholar
  19. 19.
    Li, M., Chen, S., Chen, X., Zhang, Y., Wang, Y., Tian, Q.: Actional-structural graph convolutional networks for skeleton-based action recognition. In: CVPR (2019)Google Scholar
  20. 20.
    Long, M., Cao, Z., Wang, J., Jordan, M.I.: Conditional adversarial domain adaptation. In: NIPS (2018)Google Scholar
  21. 21.
    Luo, Z., Peng, B., Huang, D.A., Alahi, A., Fei-Fei, L.: Unsupervised learning of long-term motion dynamics for videos. In: CVPR (2017)Google Scholar
  22. 22.
    van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579–2605 (2008)zbMATHGoogle Scholar
  23. 23.
    Misra, I., Zitnick, C.L., Hebert, M.: Shuffle and learn: unsupervised learning using temporal order verification. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 527–544. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46448-0_32CrossRefGoogle Scholar
  24. 24.
    Miyato, T., Maeda, S., Koyama, M., Ishii, S.: Virtual adversarial training: a regularization method for supervised and semi-supervised learning. IEEE Trans. Pattern Anal. Mach. Intell. 41, 1979–1993 (2018)CrossRefGoogle Scholar
  25. 25.
    Odena, A.: Semi-supervised learning with generative adversarial networks. arXiv preprint arXiv:1606.01583 (2016)
  26. 26.
    Rasmus, A., Berglund, M., Honkala, M., Valpola, H., Raiko, T.: Semi-supervised learning with ladder networks. In: NIPS (2015)Google Scholar
  27. 27.
    Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. In: NIPS (2016)Google Scholar
  28. 28.
    Shahroudy, A., Liu, J., Ng, T.T., Wang, G.: NTU RGB+D: a large scale dataset for 3D human activity analysis. In: CVPR (2016)Google Scholar
  29. 29.
    Shi, L., Zhang, Y., Cheng, J., Lu, H.: Two-stream adaptive graph convolutional networks for skeleton-based action recognition. In: CVPR (2019)Google Scholar
  30. 30.
    Si, C., Chen, W., Wang, W., Wang, L., Tan, T.: An attention enhanced graph convolutional LSTM network for skeleton-based action recognition. In: CVPR (2019)Google Scholar
  31. 31.
    Si, C., Jing, Y., Wang, W., Wang, L., Tan, T.: Skeleton-based action recognition with spatial reasoning and temporal stack learning. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 106–121. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01246-5_7CrossRefGoogle Scholar
  32. 32.
    Si, C., Jing, Y., Wang, W., Wang, L., Tan, T.: Skeleton-based action recognition with hierarchical spatial reasoning and temporal stack learning network. Pattern Recogn. 107, 107511 (2020)CrossRefGoogle Scholar
  33. 33.
    Srivastava, N., Mansimov, E., Salakhudinov, R.: Unsupervised learning of video representations using LSTMs. In: ICML (2015)Google Scholar
  34. 34.
    Tarvainen, A., Valpola, H.: Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. In: NIPS (2017)Google Scholar
  35. 35.
    Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: CVPR (2017)Google Scholar
  36. 36.
    Vemulapalli, R., Arrate, F., Chellappa, R.: Human action recognition by representing 3D skeletons as points in a lie group. In: CVPR (2014)Google Scholar
  37. 37.
    Vemulapalli, R., Chellappa, R.: Rolling rotations for recognizing human actions from 3D skeletal data. In: CVPR (2016)Google Scholar
  38. 38.
    Wang, J., Liu, Z., Wu, Y., Yuan, J.: Mining actionlet ensemble for action recognition with depth cameras. In: CVPR (2012)Google Scholar
  39. 39.
    Wang, J., Nie, X., Xia, Y., Wu, Y., Zhu, S.C.: Cross-view action modeling, learning, and recognition. In: CVPR (2014)Google Scholar
  40. 40.
    Wang, J., Jiao, J., Bao, L., He, S., Liu, Y., Liu, W.: Self-supervised spatio-temporal representation learning for videos by predicting motion and appearance statistics. In: CVPR (2019)Google Scholar
  41. 41.
    Wang, P., Li, Z., Hou, Y., Li, W.: Action recognition based on joint trajectory maps using convolutional neural networks. In: ACM MM (2016)Google Scholar
  42. 42.
    Wu, Z., Xiong, Y., Yu, S.X., Lin, D.: Unsupervised feature learning via non-parametric instance discrimination. In: CVPR (2018)Google Scholar
  43. 43.
    Xu, D., Xiao, J., Zhao, Z., Shao, J., Xie, D., Zhuang, Y.: Self-supervised spatiotemporal learning via video clip order prediction. In: CVPR (2019)Google Scholar
  44. 44.
    Yan, S., Xiong, Y., Lin, D., xiaoou Tang: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: AAAI (2018)Google Scholar
  45. 45.
    Zhai, X., Oliver, A., Kolesnikov, A., Beyer, L.: S4L: self-supervised semi-supervised learning. In: ICCV (2019)Google Scholar
  46. 46.
    Zhang, J., Nie, X., Feng, J.: Inference stage optimization for cross-scenario 3D human pose estimation. arXiv preprint arXiv:2007.02054 (2020)
  47. 47.
    Zhang, P., Lan, C., Xing, J., Zeng, W., Xue, J., Zheng, N.: View adaptive recurrent neural networks for high performance human action recognition from skeleton data. In: ICCV (2017)Google Scholar
  48. 48.
    Zheng, N., Wen, J., Liu, R., Long, L., Dai, J., Gong, Z.: Unsupervised representation learning with long-term dynamics for skeleton based action recognition. In: AAAI (2018)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.University of Chinese Academy of SciencesBeijingChina
  2. 2.CRIPAC & NLPR, Institute of AutomationChinese Academy of SciencesBeijingChina
  3. 3.Department of ECENational University of SingaporeSingaporeSingapore

Personalised recommendations