Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
A Theoretical Analysis of Self-Supervised Learning for Vision Transformers
2025-01-22
· ICLR 2025 Poster ·
anchor
Findings
IC-111
ViT-B/16 pretrained with MAE exhibits higher attention diversity than ViT-B/16 pretrained with MoCo v3, DINO, or DeiT