MiCE

Reported on 6 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 Vision6 results

Image ClusteringonSTL-10
Accuracy· uses extra data· 2021-05-05
0.752
best: 0.997 (TURTLE (CLIP + DINOv2))
MiCE: Mixture of Contrastive Experts for Unsupervised Image Clustering arXiv:2105.01899
Image ClusteringonSTL-10
NMI· uses extra data· 2021-05-05
0.635
best: 0.993 (TURTLE (CLIP + DINOv2))
MiCE: Mixture of Contrastive Experts for Unsupervised Image Clustering arXiv:2105.01899
Image ClusteringonImagenet-dog-15
ARI· 2021-05-05
0.286
best: 0.879 (MAE-CT (best))
MiCE: Mixture of Contrastive Experts for Unsupervised Image Clustering arXiv:2105.01899
Image ClusteringonImagenet-dog-15
Accuracy· 2021-05-05
0.439
best: 0.943 (MAE-CT (best))
MiCE: Mixture of Contrastive Experts for Unsupervised Image Clustering arXiv:2105.01899
Image ClusteringonImagenet-dog-15
Image Size· 2021-05-05
96
best: 224 (MAE-CT (best))
MiCE: Mixture of Contrastive Experts for Unsupervised Image Clustering arXiv:2105.01899
Image ClusteringonImagenet-dog-15
NMI· 2021-05-05
0.423
best: 0.904 (MAE-CT (best))
MiCE: Mixture of Contrastive Experts for Unsupervised Image Clustering arXiv:2105.01899