Estimating (and Fixing) the Effect of Face Obfuscation in Video Recognition

Matteo Tomei, Lorenzo Baraldi, Simone Bronzin, Rita Cucchiara; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2021, pp. 3263-3269

Recent research has shown that faces can be obfuscated in large-scale datasets with a minimal performance impact on image classification and downstream tasks like object recognition. In this paper, we investigate the role of face obfuscation in video classification datasets and quantify a more significant reduction in performance caused by face blurring. To reduce such performance effects, we propose a generalized distillation approach in which a privacy-preserving action recognition network is trained with privileged information given by face identities. We show, through experiments performed on Kinetics-400, that the proposed approach can fully close the performance gap caused by face anonymization.