Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN Paper • 2205.13943 • Published May 27, 2022 • 1
Switch EMA: A Free Lunch for Better Flatness and Sharpness Paper • 2402.09240 • Published Feb 14, 2024 • 3
Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning Paper • 2410.06373 • Published Oct 8, 2024 • 35