TEMI MSN (ViT-L)

Reported on 3 benchmarks across 1 task · 1 paper · 3 SOTA

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

Computer Vision3 results

Image ClusteringonImageNet
ARI· 2023-03-31
48.4
best: 62.5 (TURTLE (CLIP + DINOv2))
SOTA
Exploring the Limits of Deep Image Clustering using Pretrained Models arXiv:2303.17896
Image ClusteringonImageNet
Accuracy· 2023-03-31
61.6
best: 72.9 (TURTLE (CLIP + DINOv2))
SOTA
Exploring the Limits of Deep Image Clustering using Pretrained Models arXiv:2303.17896
Image ClusteringonImageNet
NMI· 2023-03-31
82.5
best: 88.2 (TURTLE (CLIP + DINOv2))
SOTA
Exploring the Limits of Deep Image Clustering using Pretrained Models arXiv:2303.17896