MAE-CT (mean)

Reported on 4 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 Vision4 results

Image ClusteringonImagenet-dog-15
ARI· uses extra data· 2023-04-20
0.821
best: 0.879 (MAE-CT (best))
Contrastive Tuning: A Little Help to Make Masked Autoencoders Forget arXiv:2304.10520
Image ClusteringonImagenet-dog-15
Accuracy· uses extra data· 2023-04-20
0.874
best: 0.943 (MAE-CT (best))
Contrastive Tuning: A Little Help to Make Masked Autoencoders Forget arXiv:2304.10520
Image ClusteringonImagenet-dog-15
Image Size· uses extra data· 2023-04-20
224
Contrastive Tuning: A Little Help to Make Masked Autoencoders Forget arXiv:2304.10520
Image ClusteringonImagenet-dog-15
NMI· uses extra data· 2023-04-20
0.882
best: 0.904 (MAE-CT (best))
Contrastive Tuning: A Little Help to Make Masked Autoencoders Forget arXiv:2304.10520