SOTAVerified

Unsupervised Image Classification

Models that learn to label each image (i.e. cluster the dataset into its ground truth classes) without seeing the ground truth labels.

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 21–30 of 45 papers

TitleStatusHype
Self-Supervised Classification NetworkCode1
Combining pretrained CNN feature extractors to enhance clustering of complex natural images—0
AC-VAE: Learning Semantic Representation with VAE for Adaptive Clustering—0
Improving Unsupervised Image Clustering With Robust LearningCode1
A Pseudo-labelling Auto-Encoder for unsupervised image classification—0
Unsupervised part representation by Flow Capsules—0
Unsupervised Image Classification Through Time-Multiplexed Photonic Multi-Layer Spiking Convolutional Neural Network—0
Improving Self-Organizing Maps with Unsupervised Feature ExtractionCode1
Self-Supervised Learning for Large-Scale Unsupervised Image ClusteringCode1
Unsupervised Feature Learning by Cross-Level Instance-Group DiscriminationCode1
Show:102550
← PrevPage 3 of 5Next →

No leaderboard results yet.