Abstract
Video action recognition models exhibit high performance on in-distribution data but struggle with distribution shifts in test data. To mitigate this issue, Unsupervised Domain Adaptation (UDA) methods have been proposed, consisting in training on labeled data from a source domain and incorporating unlabeled test data from a target domain to reduce the domain gap. This requires simultaneous access to data from both domains, which may not be practical in real-world scenarios due to privacy issues. A more practical approach called Source-Free Domain Adaptation (SFDA) has been recently proposed, which consists in adapting a well-trained source model using only unlabeled target data. However, existing SFDA methods are computationally intensive and designed for specific architectures. In this paper, we propose an approach called Lightweight Classification Module for Video Domain Adaptation (LCMV). LCMV is based on a backpropagation-free prototypical algorithm, which efficiently adapts a source model using unlabeled target data only. Results on two popular datasets, HMDB-UCF\(_{full}\) and EPIC-Kitchens-55, show significant improvements of LCMV compared to the previous state-of-the-art SFDA methods, and competitive results when compared to state-of-the-art UDA methods.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299–6308 (2017)
Chen, C.F.R., et al.: Deep analysis of cnn-based spatio-temporal representations for action recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6165–6175 (2021)
Chen, M.H., Kira, Z., AlRegib, G., Yoo, J., Chen, R., Zheng, J.: Temporal attentive alignment for large-scale video domain adaptation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6321–6330 (2019)
Chen, P., Ma, A.J.: Source-free temporal attentive domain adaptation for video action recognition. In: Proceedings of the 2022 International Conference on Multimedia Retrieval, pp. 489–497 (2022)
Chen, W.Y., Liu, Y.C., Kira, Z., Wang, Y.C.F., Huang, J.B.: A closer look at few-shot classification. In: International Conference on Learning Representations (2019)
Choi, J., Sharma, G., Schulter, S., Huang, J.-B.: Shuffle and attend: video domain adaptation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 678–695. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58610-2_40
Damen, D., et al.: Scaling egocentric vision: The epic-kitchens dataset. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 720–736 (2018)
Dasgupta, A., Jawahar, C., Alahari, K.: Overcoming label noise for source-free unsupervised video domain adaptation. In: ICVGIP 2022-Indian Conference on Computer Vision, Graphics and Image Processing, pp. 1–9. ACM (2022)
Fan, Q., Chen, C.F.R., Kuehne, H., Pistoia, M., Cox, D.: More is less: Learning efficient video representations by big-little network and depthwise temporal aggregation. Adv. Neural. Inf. Process. Syst. 32, 2261–2270 (2019)
Ganin, Y., Ustinova, E., Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., Marchand, M., Lempitsky, V.: Domain-adversarial training of neural networks. The J. Mach. Learn. Res. 17(1), 2030–2096 (2016)
Huang, Y., Yang, X., Zhang, J., Xu, C.: Relative alignment network for source-free multimodal video domain adaptation. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 1652–1660 (2022)
Iwasawa, Y., Matsuo, Y.: Test-time classifier adjustment module for model-agnostic domain generalization. Adv. Neural. Inf. Process. Syst. 34, 2427–2440 (2021)
Kim, D., et al.: Learning cross-modal contrastive features for video domain adaptation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 13618–13627 (2021)
Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: Hmdb: a large video database for human motion recognition. In: 2011 International Conference on Computer Vision, pp. 2556–2563. IEEE (2011)
Liang, J., Hu, D., Feng, J.: Do we really need to access the source data? source hypothesis transfer for unsupervised domain adaptation. In: International Conference on Machine Learning, pp. 6028–6039. PMLR (2020)
Lin, J., Gan, C., Han, S.: TSM: Temporal shift module for efficient video understanding. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 7083–7093 (2019)
Long, M., Cao, Y., Wang, J., Jordan, M.: Learning transferable features with deep adaptation networks. In: International Conference on Machine Learning, pp. 97–105. PMLR (2015)
Munro, J., Damen, D.: Multi-modal domain adaptation for fine-grained action recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 122–132 (2020)
Sahoo, A., Shah, R., Panda, R., Saenko, K., Das, A.: Contrast and mix: temporal contrastive video domain adaptation with background mixing. Adv. Neural. Inf. Process. Syst. 34, 23386–23400 (2021)
Singh, S., Arora, C., Jawahar, C.: First person action recognition using deep learned descriptors. In: Proceedings of the IEEE Conference On Computer Vision and Pattern Recognition, pp. 2620–2628 (2016)
Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Song, X., et al.: Spatio-temporal contrastive domain adaptation for action recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9787–9795 (2021)
Soomro, K., Zamir, A.R., Shah, M.: Ucf101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)
Torralba, A., Efros, A.A.: Unbiased look at dataset bias. In: CVPR 2011, pp. 1521–1528. IEEE (2011)
Wang, L.: Temporal segment networks: towards good practices for deep action recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 20–36. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46484-8_2
Wei, P., et al.: Unsupervised video domain adaptation: A disentanglement perspective. arXiv preprint arXiv:2208.07365 (2022)
Wu, C.Y., Feichtenhofer, C., Fan, H., He, K., Krahenbuhl, P., Girshick, R.: Long-term feature banks for detailed video understanding. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 284–293 (2019)
Xu, Y., Yang, J., Cao, H., Wu, K., Wu, M., Chen, Z.: Source-free video domain adaptation by learning temporal consistency for action recognition. In: Computer Vision-ECCV 2022: 17th European Conference. pp. 147–164. Springer (2022). https://doi.org/10.1007/978-3-031-19830-4_9
Yang, L., Huang, Y., Sugano, Y., Sato, Y.: Interact before align: Leveraging cross-modal knowledge for domain adaptive action recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14722–14732 (2022)
Zach, C., Pock, T., Bischof, H.: A duality based approach for realtime TV-L1 optical flow. In: Hamprecht, F.A., Schnörr, C., Jähne, B. (eds.) DAGM 2007. LNCS, vol. 4713, pp. 214–223. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-74936-3_22
Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 (2017)
Zhou, B., Andonian, A., Oliva, A., Torralba, A.: Temporal relational reasoning in videos. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 803–818 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Neubert, J., Planamente, M., Plizzari, C., Caputo, B. (2023). LCMV: Lightweight Classification Module for Video Domain Adaptation. In: Foresti, G.L., Fusiello, A., Hancock, E. (eds) Image Analysis and Processing – ICIAP 2023. ICIAP 2023. Lecture Notes in Computer Science, vol 14234. Springer, Cham. https://doi.org/10.1007/978-3-031-43153-1_23
Download citation
DOI: https://doi.org/10.1007/978-3-031-43153-1_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43152-4
Online ISBN: 978-3-031-43153-1
eBook Packages: Computer ScienceComputer Science (R0)