Image Clustering On Cifar 100

Metriken

ARI

Accuracy

NMI

Train Set

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

					Paper Title
TURTLE (CLIP + DINOv2)	0.834	0.898	0.915	-	Let Go of Your Labels with Unsupervised Transfer
PRCut (DinoV2)	-	0.789	0.856	-	Deep Clustering via Probabilistic Ratio-Cut Optimization
PRO-DSC	-	0.773	0.824	-	Exploring a Principled Framework For Deep Subspace Clustering
TEMI CLIP ViT-L (openai)	0.612	0.737	0.799	Train	Exploring the Limits of Deep Image Clustering using Pretrained Models
TEMI DINO ViT-B	0.533	0.671	0.769	Train	Exploring the Limits of Deep Image Clustering using Pretrained Models
ITAE	0.5053	0.6502	0.771	Test	Improving Image Clustering with Artifacts Attenuation via Inference-Time Attention Engineering
SPICE*	0.422	0.584	0.583	Train	SPICE: Semantic Pseudo-labeling for Image Clustering
HUME	0.377	0.555	-	Train	-
DPAC	0.393	0.555	0.542	-	Deep Online Probability Aggregation Clustering
SPICE-BPA	0.402	0.550	0.560	-	The Balanced-Pairwise-Affinities Feature Transform
TCL	0.357	0.531	0.529	Train	Twin Contrastive Learning for Online Clustering
IMC-SwAV (Best)	0.361	0.519	0.527	Train	Information Maximization Clustering via Multi-View Self-Labelling
SCAN	0.333	0.507	0.486	Train	SCAN: Learning to Classify Images without Labels
IMC-SwAV (Avg+-)	0.337	0.49	0.503	-	Information Maximization Clustering via Multi-View Self-Labelling
ConCURL	0.303	0.479	0.468	Train	Representation Learning for Clustering via Building Consensus
SCAN (Avg)	0.301	0.459	0.468	Train	SCAN: Learning to Classify Images without Labels
C3	0.275	0.451	0.434	-	C3: Cross-instance guided Contrastive Clustering
MMDC	-	0.446	0.418	-	Multi-Modal Deep Clustering: Unsupervised Partitioning of Images
CoHiClust	0.299	0.437	0.467	-	Contrastive Hierarchical Clustering
CC	0.266	0.429	0.431	-	Contrastive Clustering

0 of 30 row(s) selected.

Command Palette

Image Clustering On Cifar 100

Metriken

Ergebnisse