Image Clustering On Imagenet 100
Métriques
ACCURACY
ARI
NMI
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | ACCURACY | ARI | NMI | Paper Title | Repository |
|---|---|---|---|---|---|
| Single-Noun Prior | 0.731 | 0.628 | 0.805 | Dataset Summarization by K Principal Concepts | - |
| TEMI CLIP ViT-L (openai) | 0.8343 | 0.7581 | 0.9006 | Exploring the Limits of Deep Image Clustering using Pretrained Models | |
| TEMI MSN ViT-L | 0.8286 | 0.7408 | 0.8853 | Exploring the Limits of Deep Image Clustering using Pretrained Models | |
| SCAN | 0.662 | 0.544 | 0.787 | SCAN: Learning to Classify Images without Labels | |
| TEMI DINO ViT-B | 0.7505 | 0.6545 | 0.8565 | Exploring the Limits of Deep Image Clustering using Pretrained Models |
0 of 5 row(s) selected.