Efficient Image Pre-Training with Siamese Cropped Masked Autoencoders

1 code implementation • 26 Mar 2024 • Alexandre Eymaël, Renaud Vandeghen, Anthony Cioppa, Silvio Giancola, Bernard Ghanem, Marc Van Droogenbroeck

In particular, SiamMAE recently introduced a Siamese network, training a shared-weight encoder from two frames of a video with a high asymmetric masking ratio (95%).

Self-Supervised Learning