Incremental Learning Techniques Within a Self-updating Approach for Face Verification in Video-Surveillance
Data labelling is still a crucial task which precedes the training of a face verification system. In contexts where training data are obtained online during operational stages, and/or the genuine identity changes over time, supervised approaches are less suitable.
This work proposes a face verification system capable of autonomously generating a robust model of a target identity (genuine) from a very limited amount of labelled data (one or a few video frames). A self-updating approach is used to wrap two well known incremental learning techniques, namely Incremental SVM and Online Sequential ELM.
The performance of both strategies are compared by measuring their ability to unsupervisedly improve the model of the genuine identity over time, as the system is queried by both genuine and impostor identities. Results confirm the feasibility and potential of the self-updating approach in a video-surveillance context.
KeywordsFace verification Video-surveillance Incremental learning Self-updating
This work has received financial support from the Spanish government (project TIN2017-90135-R MINECO (FEDER)), from The Consellería de Cultura, Educación e Ordenación Universitaria (accreditations 2016–2019, EDG431G/01 and ED431G/08), and reference competitive groups (2017–2020 ED431C 2017/69, and ED431C 2017/04), and from the European Regional Development Fund (ERDF). Eric López had received financial support from the Xunta de Galicia and the European Union (European Social Fund - ESF).
- 10.He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016). https://doi.org/10.1109/CVPR.2016.90
- 18.Masi, I., Wu, Y., Hassner, T., Natarajan, P.: Deep face recognition: A survey. In: Conference on Graphics, Patterns and Images (SIBGRAPI), pp. 471–478 (2018). https://doi.org/10.1109/SIBGRAPI.2018.00067
- 19.Pernici, F., Bartoli, F., Bruni, M., Del Bimbo, A.: Memory based online learning of deep representations from video streams. In: Computer Vision and Pattern Recognition (CVPR), pp. 2324–2334 (2018). https://doi.org/10.1109/CVPR.2018.00247
- 20.Pernici, F., Bimbo, A.D.: Unsupervised incremental learning of deep descriptors from video streams. In: International Conference on Multimedia Expo Workshops (ICMEW), pp. 477–482 (2017). https://doi.org/10.1109/ICMEW.2017.8026276
- 21.Sohn, K., Liu, S., Zhong, G., Yu, X., Yang, M., Chandraker, M.: Unsupervised domain adaptation for face recognition in unlabeled videos. In: International Conference on Computer Vision (ICCV), pp. 5917–5925 (2017). https://doi.org/10.1109/ICCV.2017.630
- 23.Wang, R., Shan, S., Chen, X., Gao, W.: Manifold-manifold distance with application to face recognition based on image set. In: Computer Vision and Pattern Recognition (CVPR), pp. 1–8 (2008). https://doi.org/10.1109/CVPR.2008.4587719
- 24.Wang, X., Gupta, A.: Unsupervised learning of visual representations using videos. In: International Conference on Computer Vision (ICCV), pp. 2794–2802 (2015). https://doi.org/10.1109/ICCV.2015.320
- 25.Yarowsky, D.: Unsupervised word sense disambiguation rivaling supervised methods. In: Annual Meeting on Association for Computational Linguistics (ACL), pp. 189–196. Association for Computational Linguistics, Stroudsburg, PA, USA (1995). https://doi.org/10.3115/981658.981684