DINOv2+reg (ViT-g/14)

Reported on 1 benchmark across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision1 result

Image ClassificationonImageNet
Top 1 Accuracy· uses extra data· 2023-09-28
87.1
best: 88.3 (Unicom (ViT-L/14@336px) (Finetuned))
Vision Transformers Need Registers arXiv:2309.16588