research
∙
09/07/2023
DropPos: Pre-Training Vision Transformers by Reconstructing Dropped Positions
As it is empirically observed that Vision Transformers (ViTs) are quite ...
share
research
∙
04/13/2023
Multi-Mode Online Knowledge Distillation for Self-Supervised Visual Representation Learning
Self-supervised learning (SSL) has made remarkable progress in visual re...
research
∙
04/12/2023
Hard Patches Mining for Masked Image Modeling
Masked image modeling (MIM) has attracted much research attention due to...
research
∙
12/13/2022