Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Willette, Jeffrey Ryan"'
The Masked autoencoder (MAE) has drawn attention as a representative self-supervised approach for masked image modeling with vision transformers. However, even though MAE shows better generalization capability than fully supervised training from scra
Externí odkaz:
http://arxiv.org/abs/2405.18042
