Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/TEMI DINO ViT-B

TEMI DINO ViT-B

Reported on 17 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 Vision17 results

Image ClusteringonSTL-10
ARI· uses extra data· 2023-03-31
0.968
best: 0.994 (TURTLE (CLIP + DINOv2))
SOTA
Exploring the Limits of Deep Image Clustering using Pretrained Models arXiv:2303.17896
Image ClusteringonSTL-10
Accuracy· uses extra data· 2023-03-31
0.985
best: 0.997 (TURTLE (CLIP + DINOv2))
SOTA
Exploring the Limits of Deep Image Clustering using Pretrained Models arXiv:2303.17896
Image ClusteringonSTL-10
NMI· uses extra data· 2023-03-31
0.965
best: 0.993 (TURTLE (CLIP + DINOv2))
SOTA
Exploring the Limits of Deep Image Clustering using Pretrained Models arXiv:2303.17896
Image ClusteringonImageNet-100 (TEMI Split)
ACCURACY· uses extra data· 2023-03-31
0.7505
best: 0.8343 (TEMI CLIP ViT-L (openai))
Exploring the Limits of Deep Image Clustering using Pretrained Models arXiv:2303.17896
Image ClusteringonImageNet-100 (TEMI Split)
ARI· uses extra data· 2023-03-31
0.6545
best: 0.7581 (TEMI CLIP ViT-L (openai))
Exploring the Limits of Deep Image Clustering using Pretrained Models arXiv:2303.17896
Image ClusteringonImageNet-100 (TEMI Split)
NMI· uses extra data· 2023-03-31
0.8565
best: 0.9006 (TEMI CLIP ViT-L (openai))
Exploring the Limits of Deep Image Clustering using Pretrained Models arXiv:2303.17896
Image ClusteringonCIFAR-10
ARI· uses extra data· 2023-03-31
0.885
best: 0.989 (TURTLE (CLIP + DINOv2))
Exploring the Limits of Deep Image Clustering using Pretrained Models arXiv:2303.17896
Image ClusteringonCIFAR-10
NMI· uses extra data· 2023-03-31
0.886
best: 0.985 (TURTLE (CLIP + DINOv2))
Exploring the Limits of Deep Image Clustering using Pretrained Models arXiv:2303.17896
Image ClusteringonCIFAR-100
ARI· uses extra data· 2023-03-31
0.533
best: 0.834 (TURTLE (CLIP + DINOv2))
Exploring the Limits of Deep Image Clustering using Pretrained Models arXiv:2303.17896
Image ClusteringonCIFAR-100
Accuracy· uses extra data· 2023-03-31
0.671
best: 0.898 (TURTLE (CLIP + DINOv2))
Exploring the Limits of Deep Image Clustering using Pretrained Models arXiv:2303.17896
Image ClusteringonCIFAR-100
NMI· uses extra data· 2023-03-31
0.769
best: 0.915 (TURTLE (CLIP + DINOv2))
Exploring the Limits of Deep Image Clustering using Pretrained Models arXiv:2303.17896
Image ClusteringonImageNet-200
ACCURACY· uses extra data· 2023-03-31
0.7312
best: 0.7776 (TEMI CLIP ViT-L (openai))
Exploring the Limits of Deep Image Clustering using Pretrained Models arXiv:2303.17896
Image ClusteringonImageNet-200
ARI· uses extra data· 2023-03-31
0.6231
best: 0.6941 (TEMI CLIP ViT-L (openai))
Exploring the Limits of Deep Image Clustering using Pretrained Models arXiv:2303.17896
Image ClusteringonImageNet-200
NMI· uses extra data· 2023-03-31
0.852
best: 0.8839 (TEMI CLIP ViT-L (openai))
Exploring the Limits of Deep Image Clustering using Pretrained Models arXiv:2303.17896
Image ClusteringonImageNet-50 (TEMI Split)
ACCURACY· uses extra data· 2023-03-31
0.801
best: 0.8827 (TEMI CLIP ViT-L (openai))
Exploring the Limits of Deep Image Clustering using Pretrained Models arXiv:2303.17896
Image ClusteringonImageNet-50 (TEMI Split)
ARI· uses extra data· 2023-03-31
0.7093
best: 0.8272 (TEMI CLIP ViT-L (openai))
Exploring the Limits of Deep Image Clustering using Pretrained Models arXiv:2303.17896
Image ClusteringonImageNet-50 (TEMI Split)
NMI· uses extra data· 2023-03-31
0.861
best: 0.9232 (TEMI CLIP ViT-L (openai))
Exploring the Limits of Deep Image Clustering using Pretrained Models arXiv:2303.17896