Self-supervised pre-training has been proved to be effective in learning transferable
representations that benefit various visual tasks. This paper asks this question: can self …

This work asks: with abundant, unlabeled real faces, how to learn a robust and transferable
facial representation that boosts various face security tasks with respect to generalization …

This study demonstrates a novel approach to facial camouflage that combines targeted
cosmetic perturbations and alpha transparency layer manipulation to evade modern facial …

Recent progress in self-supervised representation learning has shown that self-supervised
pre-training can leverage unlabeled data to learn generalizable representations that benefit …