CL-MAE: Curriculum-Learned Masked Autoencoders

arXiv:2308.16572v3 Announce Type: replace-cross
Abstract: Masked image modeling has been demonstrated as a powerful pretext task for generating robust representations that can be effectively generalized across multiple downstream tasks. Typically, this approach involves randomly masking patches (tokens) in input images, with the masking strategy remaining unchanged during training. In this paper, we propose a curriculum learning approach that updates the masking strategy to continually increase the complexity of the self-supervised reconstruction task. We conjecture that, by gradually increasing the task …

arxiv autoencoders cs.ai cs.cv cs.lg curriculum type