Let Go of Your Labels with Unsupervised Transfer

Open paper

Benchmark	Model	Rank	Results
image-clustering-on-cifar-10	TURTLE (CLIP + DINOv2)	#1	Accuracy: 0.995NMI: 0.985ARI: 0.989
image-clustering-on-cifar-100	TURTLE (CLIP + DINOv2)	#1	Accuracy: 0.898NMI: 0.915ARI: 0.834
image-clustering-on-imagenet	TURTLE (CLIP + DINOv2)	#1	Accuracy: 72.9NMI: 88.2ARI: 62.5
image-clustering-on-mnist	TURTLE (CLIP + DINOv2)	#2	Accuracy: 97.8
image-clustering-on-stanford-cars	TURTLE (CLIP + DINOv2)	#1	Accuracy: 0.646
image-clustering-on-stl-10	TURTLE (CLIP + DINOv2)	#1	Accuracy: 0.997NMI: 0.993ARI: 0.994
unsupervised-image-classification-on-cifar-10	TURTLE (CLIP + DINOv2)	#1	Accuracy: 99.5
unsupervised-image-classification-on-imagenet	TURTLE (CLIP + DINOv2)	#1	Accuracy (%): 72.9ARI: 62.5
unsupervised-image-classification-on-mnist	TURTLE (CLIP + DINOv2)	#2	Accuracy: 97.8
unsupervised-image-classification-on-stl-10	TURTLE (CLIP + DINOv2)	#1	Accuracy: 99.7