ImageNet-1K Self-Supervised ViT Baselines
Collection
A collection of open and reproducible self-supervised Vision Transformer (ViT) checkpoints trained exclusively on ImageNet-1K (1.43M images). • 7 items • Updated • 1
Mei
Tenbatsu2424
·
AI & ML interests
None yet
Recent Activity
updated a model 1 day ago
OK-AI/dino-vitb16-pretrain-in1k upvoted a collection 2 days ago
ImageNet-1K Self-Supervised ViT Baselines liked a Space 4 days ago
OK-AI/ViT-Patch-PCA-VisualisationOrganizations
upvoted a collection 2 days ago