Dominick Reilly will present "Limited Data, Unlimited Potential: A Study on ViTs Augmented by Masked Autoencoders" at WACV 2024 in Hawaii

This paper shows that jointly optimizing Vision Transformers for the primary task and a Self-Supervised Auxiliary Task is surprisingly beneficial when the amount of training data is limited.

Link to the paper: https://arxiv.org/abs/2310.20704