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 1–10 of 45 papers

TitleStatusHype
Breaking the Reclustering Barrier in Centroid-based Deep ClusteringCode1
Let Go of Your Labels with Unsupervised TransferCode2
IPCL: Iterative Pseudo-Supervised Contrastive Learning to Improve Self-Supervised Feature RepresentationCode0
The VampPrior Mixture ModelCode0
Improving Cross-domain Few-shot Classification with Multilayer PerceptronCode1
Stable Cluster Discrimination for Deep ClusteringCode1
The Pursuit of Human Labeling: A New Perspective on Unsupervised LearningCode1
Contrastive Knowledge Amalgamation for Unsupervised Image Classification—0
ContraCluster: Learning to Classify without Labels by Contrastive Self-Supervision and Prototype-Based Semi-Supervision—0
MV-MR: multi-views and multi-representations for self-supervised learning and knowledge distillationCode0
Show:102550
← PrevPage 1 of 5Next →

No leaderboard results yet.