SOTAVerified

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

Showing 1–50 of 236 papers

TitleStatusHype
Structural-Spectral Graph Convolution with Evidential Edge Learning for Hyperspectral Image ClusteringCode0
Unsupervised Deep Clustering of MNIST with Triplet-Enhanced Convolutional Autoencoders—0
Advanced Clustering Framework for Semiconductor Image Analytics Integrating Deep TDA with Self-Supervised and Transfer Learning Techniques—0
Utilization of Neighbor Information for Image Classification with Different Levels of Supervision—0
Online Meta-learning for AutoML in Real-time (OnMAR)—0
Keep It Light! Simplifying Image Clustering Via Text-Free Adapters—0
Deep Clustering via Probabilistic Ratio-Cut OptimizationCode0
Graph Cut-guided Maximal Coding Rate Reduction for Learning Image Embedding and ClusteringCode0
DiFiC: Your Diffusion Model Holds the Secret to Fine-Grained Clustering—0
I Spy With My Little Eye: A Minimum Cost Multicut Investigation of Dataset FramesCode0
Breaking the Reclustering Barrier in Centroid-based Deep ClusteringCode1
Improving Image Clustering with Artifacts Attenuation via Inference-Time Attention Engineering—0
Dual-Level Cross-Modal Contrastive ClusteringCode0
Deep Clustering of Remote Sensing Scenes through Heterogeneous Transfer Learning—0
Dual Advancement of Representation Learning and Clustering for Sparse and Noisy ImagesCode0
Clustering-friendly Representation Learning for Enhancing Salient Features—0
Image Clustering Algorithm Based on Self-Supervised Pretrained Models and Latent Feature Distribution OptimizationCode0
Deep Online Probability Aggregation ClusteringCode0
Funny-Valen-Tine: Planning Solution Distribution Enhances Machine Abstract Reasoning Ability—0
The Balanced-Pairwise-Affinities Feature TransformCode2
Let Go of Your Labels with Unsupervised TransferCode2
Text-Guided Alternative Image Clustering—0
Scaling Up Deep Clustering Methods Beyond ImageNet-1K—0
Towards Realistic Long-tailed Semi-supervised Learning in an Open WorldCode0
Autonomous clustering by fast find of mass and distance peaksCode2
Contrastive Mean-Shift Learning for Generalized Category Discovery—0
Multi-level Graph Subspace Contrastive Learning for Hyperspectral Image Clustering—0
Terraced Compression Method with Automated Threshold Selection for Multidimensional Image Clustering of Heterogeneous Bodies—0
IPCL: Iterative Pseudo-Supervised Contrastive Learning to Improve Self-Supervised Feature RepresentationCode0
Rethinking cluster-conditioned diffusion models for label-free image synthesisCode0
MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained RepresentationsCode1
The VampPrior Mixture ModelCode0
Text-Guided Image ClusteringCode1
Learning Representations for Clustering via Partial Information Discrimination and Cross-Level InteractionCode0
Multi-level Cross-modal Alignment for Image Clustering—0
Deep Structure and Attention Aware Subspace ClusteringCode0
Superpixel-based and Spatially-regularized Diffusion Learning for Unsupervised Hyperspectral Image ClusteringCode1
Image Clustering using Restricted Boltzman Machine—0
Pixel-Superpixel Contrastive Learning and Pseudo-Label Correction for Hyperspectral Image Clustering—0
Stable Cluster Discrimination for Deep ClusteringCode1
Patch-Based Deep Unsupervised Image Segmentation using Graph Cuts—0
Grid Jigsaw Representation with CLIP: A New Perspective on Image Clustering—0
Image Clustering Conditioned on Text CriteriaCode1
Image Clustering with External GuidanceCode1
Quantum Block-Matching Algorithm using Dissimilarity Measure—0
The Pursuit of Human Labeling: A New Perspective on Unsupervised LearningCode1
Bridging Distribution Learning and Image Clustering in High-dimensional Space—0
MES-Loss: Mutually equidistant separation metric learning loss function—0
Image Clustering via the Principle of Rate Reduction in the Age of Pretrained ModelsCode1
Contrastive Tuning: A Little Help to Make Masked Autoencoders ForgetCode1
Show:102550
← PrevPage 1 of 5Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1TURTLE (CLIP + DINOv2)Accuracy1—Unverified
2PRCut (CLIP)Accuracy0.98—Unverified
3PRO-DSCAccuracy0.97—Unverified
4TEMI CLIP ViT-L (openai)Accuracy0.97—Unverified
5DPACAccuracy0.93—Unverified
6SPICE-BPAAccuracy0.93—Unverified
7SeCuAccuracy0.93—Unverified
8TACAccuracy0.92—Unverified
9SPICE*Accuracy0.92—Unverified
10DCN+BRBAccuracy0.91—Unverified
#ModelMetricClaimedVerifiedStatus
1TURTLE (CLIP + DINOv2)Accuracy0.9—Unverified
2PRCut (DinoV2)Accuracy0.79—Unverified
3PRO-DSCAccuracy0.77—Unverified
4TEMI CLIP ViT-L (openai)Accuracy0.74—Unverified
5TEMI DINO ViT-BAccuracy0.67—Unverified
6ITAEAccuracy0.65—Unverified
7SPICE*Accuracy0.58—Unverified
8DPACAccuracy0.56—Unverified
9HUMEAccuracy0.56—Unverified
10SPICE-BPAAccuracy0.55—Unverified
#ModelMetricClaimedVerifiedStatus
1TURTLE (CLIP + DINOv2)Accuracy1—Unverified
2TEMI DINO ViT-BAccuracy0.99—Unverified
3TACAccuracy0.98—Unverified
4SPICE-BPAAccuracy0.94—Unverified
5DPACAccuracy0.93—Unverified
6SPICE*Accuracy0.93—Unverified
7HUMEAccuracy0.91—Unverified
8TCLAccuracy0.87—Unverified
9RUCAccuracy0.87—Unverified
10IMC-SwAV (Best)Accuracy0.85—Unverified
#ModelMetricClaimedVerifiedStatus
1MAE-CT (best)Accuracy0.94—Unverified
2MAE-CT (mean)Accuracy0.87—Unverified
3PRO-DSCAccuracy0.84—Unverified
4ProPos*Accuracy0.78—Unverified
5ProPosAccuracy0.75—Unverified
6DPACAccuracy0.73—Unverified
7ConCURLAccuracy0.7—Unverified
8SPICEAccuracy0.68—Unverified
9TCLAccuracy0.64—Unverified
10IDFDAccuracy0.59—Unverified
#ModelMetricClaimedVerifiedStatus
1TACNMI0.99—Unverified
2SPICENMI0.93—Unverified
3DPACNMI0.93—Unverified
4ProPos*NMI0.91—Unverified
5ConCURLNMI0.91—Unverified
6CoHiClustNMI0.91—Unverified
7C3NMI0.91—Unverified
8IDFDNMI0.9—Unverified
9ProPosNMI0.9—Unverified
10TCLNMI0.88—Unverified
#ModelMetricClaimedVerifiedStatus
1SPCNMI0.98—Unverified
2ADECNMI0.97—Unverified
3N2D (UMAP)NMI0.96—Unverified
4DynAENMI0.96—Unverified
5DDC-DANMI0.96—Unverified
6DENNMI0.96—Unverified
7DTI-ClusteringNMI0.94—Unverified
8EnSCNMI0.94—Unverified
9ClusterGANNMI0.94—Unverified
10DBCNMI0.94—Unverified
#ModelMetricClaimedVerifiedStatus
1SPCNMI0.95—Unverified
2DynAENMI0.95—Unverified
3DENNMI0.94—Unverified
4DDC-DANMI0.94—Unverified
5SR-K-meansNMI0.94—Unverified
6ClusterGANNMI0.93—Unverified
7DMSCNMI0.93—Unverified
8DDCNMI0.92—Unverified
9JULE-RCNMI0.91—Unverified
10N2D (UMAP)NMI0.9—Unverified
#ModelMetricClaimedVerifiedStatus
1PRO-DSCAccuracy0.7—Unverified
2ITAEAccuracy0.68—Unverified
3SPICEAccuracy0.31—Unverified
4IMC-SwAV (Best)Accuracy0.28—Unverified
5IMC-SwAV (Avg+-)Accuracy0.28—Unverified
6C3Accuracy0.14—Unverified
7CCAccuracy0.14—Unverified
8MMDCAccuracy0.12—Unverified
9DCCMAccuracy0.11—Unverified
10DACAccuracy0.07—Unverified
#ModelMetricClaimedVerifiedStatus
1PRCut (DinoV2)Accuracy0.79—Unverified
2VMMAccuracy0.72—Unverified
3SPCAccuracy0.68—Unverified
4N2D (UMAP)Accuracy0.67—Unverified
5CoHiClustAccuracy0.65—Unverified
6DENAccuracy0.64—Unverified
7PSSCAccuracy0.63—Unverified
8GDLAccuracy0.63—Unverified
9DDCAccuracy0.62—Unverified
10DTI-ClusteringAccuracy0.61—Unverified
#ModelMetricClaimedVerifiedStatus
1TURTLE (CLIP + DINOv2)Accuracy72.9—Unverified
2MIM-Refiner (D2V2-ViT-H/14)Accuracy67.3—Unverified
3SeLaNMI66.4—Unverified
4PRO-DSCAccuracy65—Unverified
5MIM-Refiner (MAE-ViT-H/14)Accuracy64.6—Unverified