SupMAE: Supervised Masked Autoencoders Are Efficient Vision Learners. (arXiv:2205.14540v2 [cs.CV] UPDATED)

Recently, self-supervised Masked Autoencoders (MAE) have attracted
unprecedented attention for their impressive representation learning ability.
However, the pretext task, Masked Image Modeling (MIM), reconstructs the
missing local patches, lacking the global understanding of the image. This
paper extends MAE to a fully-supervised setting by adding a supervised
classification branch, thereby enabling MAE to effectively learn global
features from golden labels. The proposed Supervised MAE (SupMAE) only exploits
a visible subset of image patches for classification, unlike the standard
supervised pre-training …

arxiv cv vision