MIM-Refiner (D2V2-ViT-H/14)

Reported on 3 benchmarks across 1 task · 1 paper · 2 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
Accuracy· 2024-02-15
67.3
best: 72.9 (TURTLE (CLIP + DINOv2))
SOTA
MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Representations arXiv:2402.10093
Image ClusteringonImageNet
NMI· 2024-02-15
87.2
best: 88.2 (TURTLE (CLIP + DINOv2))
SOTA
MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Representations arXiv:2402.10093
Image ClusteringonImageNet
ARI· 2024-02-15
42.2
best: 62.5 (TURTLE (CLIP + DINOv2))
MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Representations arXiv:2402.10093