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

Showing 1120 of 45 papers

TitleStatusHype
Breaking the Reclustering Barrier in Centroid-based Deep ClusteringCode1
Improving Cross-domain Few-shot Classification with Multilayer PerceptronCode1
Improving Self-Organizing Maps with Unsupervised Feature ExtractionCode1
Improving Unsupervised Image Clustering With Robust LearningCode1
InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial NetsCode1
Capsule Network based Contrastive Learning of Unsupervised Visual RepresentationsCode1
Self-Supervised Classification NetworkCode1
Deep Transformation-Invariant ClusteringCode1
Self-Supervised Learning for Large-Scale Unsupervised Image ClusteringCode1
Unsupervised Deep Embedding for Clustering AnalysisCode1
Show:102550
← PrevPage 2 of 5Next →

No leaderboard results yet.