MAE-CT (ViT-H/16 best)

Reported on 2 benchmarks 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 Vision2 results

Image ClusteringonImageNet
Accuracy· 2023-04-20
58
best: 72.9 (TURTLE (CLIP + DINOv2))
Contrastive Tuning: A Little Help to Make Masked Autoencoders Forget arXiv:2304.10520
Image ClusteringonImageNet
NMI· 2023-04-20
81.8
best: 88.2 (TURTLE (CLIP + DINOv2))
Contrastive Tuning: A Little Help to Make Masked Autoencoders Forget arXiv:2304.10520