Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty

Self-supervised learning holds great promise for improving representations when labeled data are scarce. In semi-supervised learning, recent self-supervision methods are state-of-the-art [Gidaris et al., 2018, Dosovitskiy et al., 2016, Zhai et al., 2019], and self-supervision is essential in video tasks where annotation is costly [V ondrick et al., 2016, 2018].