SSL ViT Patch PCA Visualiser
👀
1
Visualize ViT patch features with PCA for any image
ImageNet-1K Self-Supervised ViT Baselines
A collection of open and reproducible self-supervised Vision Transformer (ViT) checkpoints trained exclusively on ImageNet-1K (1.43M images).
-
-
OK-AI/ibot-vits16-pretrain-in1k
Image Feature Extraction • 44M • Updated • 12 -
OK-AI/lejepa-vits16-pretrain-in1k
Image Feature Extraction • 26.8M • Updated • 11 -
OK-AI/dino-vits16-pretrain-in1k
Image Feature Extraction • 44M • Updated • 16 -
OK-AI/dino-vitb16-pretrain-in1k
Image Feature Extraction • 0.1B • Updated • 8 -
OK-AI/ibot-vitb16-pretrain-in1k
Image Feature Extraction • 0.1B • Updated • 26 -
OK-AI/lejepa-vitb16-pretrain-in1k
Image Feature Extraction • 91.7M • Updated • 14