SOTAVerified|Agents Browse Leaderboard About

Image Clustering

Models that partition the dataset into semantically meaningful clusters without having access to the ground truth labels.

Image credit: ImageNet clustering results of SCAN: Learning to Classify Images without Labels (ECCV 2020)

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 1–10 of 236 papers

Title	Date	Tasks	Status	Hype
Structural-Spectral Graph Convolution with Evidential Edge Learning for Hyperspectral Image Clustering	Jun 11, 2025	ClusteringContrastive Learning	CodeCode Available	0
Unsupervised Deep Clustering of MNIST with Triplet-Enhanced Convolutional Autoencoders	Jun 11, 2025	ClusteringDeep Clustering	—Unverified	0
Advanced Clustering Framework for Semiconductor Image Analytics Integrating Deep TDA with Self-Supervised and Transfer Learning Techniques	May 5, 2025	ClusteringImage Clustering	—Unverified	0
Utilization of Neighbor Information for Image Classification with Different Levels of Supervision	Mar 18, 2025	Clusteringimage-classification	—Unverified	0
Online Meta-learning for AutoML in Real-time (OnMAR)	Feb 27, 2025	AutoMLImage Clustering	—Unverified	0
Keep It Light! Simplifying Image Clustering Via Text-Free Adapters	Feb 6, 2025	ClusteringDeep Clustering	—Unverified	0
Deep Clustering via Probabilistic Ratio-Cut Optimization	Feb 1, 2025	ClusteringDeep Clustering	CodeCode Available	0
DiFiC: Your Diffusion Model Holds the Secret to Fine-Grained Clustering	Dec 25, 2024	ClusteringData Augmentation	—Unverified	0
Graph Cut-guided Maximal Coding Rate Reduction for Learning Image Embedding and Clustering	Dec 25, 2024	ClusteringImage Clustering	CodeCode Available	0
I Spy With My Little Eye: A Minimum Cost Multicut Investigation of Dataset Frames	Dec 2, 2024	ClusteringImage Clustering	CodeCode Available	0

Show:10 25 50

← PrevPage 1 of 24Next →

All datasets CIFAR-10 CIFAR-100 STL-10 Imagenet-dog-15 ImageNet-10 MNIST-full USPS Tiny ImageNet Fashion-MNIST ImageNet MNIST-test coil-100

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	TURTLE (CLIP + DINOv2)	Accuracy	1	—	Unverified
2	PRCut (CLIP)	Accuracy	0.98	—	Unverified
3	PRO-DSC	Accuracy	0.97	—	Unverified
4	TEMI CLIP ViT-L (openai)	Accuracy	0.97	—	Unverified
5	DPAC	Accuracy	0.93	—	Unverified
6	SPICE-BPA	Accuracy	0.93	—	Unverified
7	SeCu	Accuracy	0.93	—	Unverified
8	TAC	Accuracy	0.92	—	Unverified
9	SPICE*	Accuracy	0.92	—	Unverified
10	DCN+BRB	Accuracy	0.91	—	Unverified