Image Clustering On Cifar 10

评估指标

ARI

Accuracy

Backbone

NMI

Train set

评测结果

各个模型在此基准测试上的表现结果

						Paper Title	Repository
TURTLE (CLIP + DINOv2)	0.989	0.995	-	0.985	-	Let Go of Your Labels with Unsupervised Transfer
PRCut (CLIP)	-	0.975	-	0.934	-	Deep Clustering via Probabilistic Ratio-Cut Optimization	-
PRO-DSC	-	0.972	-	0.928	-	Exploring a Principled Framework For Deep Subspace Clustering	-
TEMI CLIP ViT-L (openai)	0.932	0.969	ViT-L	0.926	Train	Exploring the Limits of Deep Image Clustering using Pretrained Models
TEMI DINO ViT-B	0.885	0.94.5	ViT-B	0.886	Train	Exploring the Limits of Deep Image Clustering using Pretrained Models
DPAC	0.866	0.934	ResNet-34	0.87	-	Deep Online Probability Aggregation Clustering
SPICE-BPA	0.866	0.933	ResNet-18	0.870	-	The Balanced-Pairwise-Affinities Feature Transform
SeCu	0.857	0.93	ResNet-18	0.861	Train	Stable Cluster Discrimination for Deep Clustering
TAC	0.831	0.919	-	0.833	-	Image Clustering with External Guidance
SPICE*	0.836	0.918	ResNet-18	0.850	Train	SPICE: Semantic Pseudo-labeling for Image Clustering
DCN+BRB	0.824	0.912	ResNet-18	0.837	Train	Breaking the Reclustering Barrier in Centroid-based Deep Clustering
IDEC+BRB	0.818	0.907	ResNet-18	0.833	Train	Breaking the Reclustering Barrier in Centroid-based Deep Clustering
DEC+BRB	0.812	0.906	ResNet-18	0.826	Train	Breaking the Reclustering Barrier in Centroid-based Deep Clustering
RUC	-	0.903	ResNet-18	-	-	Improving Unsupervised Image Clustering With Robust Learning
IMC-SwAV (Best)	0.8	0.897	ResNet-18	0.818	Train	Information Maximization Clustering via Multi-View Self-Labelling
IMC-SwAV (Avg+-)	0.79	0.891	ResNet-18	0.811	Train	Information Maximization Clustering via Multi-View Self-Labelling
TCL	0.780	0.887	ResNet-34	0.819	Train	Twin Contrastive Learning for Online Clustering
HUME	0.776	0.884	ResNet-18	-	Train	-	-
SCAN	0.772	0.883	ResNet-18	0.797	Train	SCAN: Learning to Classify Images without Labels
SCAN (Avg)	0.758	0.876	ResNet-18	0.787	Train	SCAN: Learning to Classify Images without Labels

0 of 40 row(s) selected.