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 31–40 of 45 papers

TitleStatusHype
GUIDED MCMC FOR SPARSE BAYESIAN MODELS TO DETECT RARE EVENTS IN IMAGES SANS LABELED DATA—0
A Pseudo-labelling Auto-Encoder for unsupervised image classification—0
Self-supervised classification of dynamic obstacles using the temporal information provided by videos—0
Unsupervised part representation by Flow Capsules—0
AC-VAE: Learning Semantic Representation with VAE for Adaptive Clustering—0
Unsupervised Image Classification Through Time-Multiplexed Photonic Multi-Layer Spiking Convolutional Neural Network—0
LatentGAN Autoencoder: Learning Disentangled Latent Distribution—0
ContraCluster: Learning to Classify without Labels by Contrastive Self-Supervision and Prototype-Based Semi-Supervision—0
Learning Latent Representations in Neural Networks for Clustering through Pseudo Supervision and Graph-based Activity Regularization—0
Combining pretrained CNN feature extractors to enhance clustering of complex natural images—0
Show:102550
← PrevPage 4 of 5Next →

No leaderboard results yet.