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 2645 of 45 papers

TitleStatusHype
The VampPrior Mixture ModelCode0
IPCL: Iterative Pseudo-Supervised Contrastive Learning to Improve Self-Supervised Feature RepresentationCode0
MV-MR: multi-views and multi-representations for self-supervised learning and knowledge distillationCode0
Learning Discrete Representations via Information Maximizing Self-Augmented TrainingCode0
PixelGAN AutoencodersCode0
A Pseudo-labelling Auto-Encoder for unsupervised image classification0
Self-supervised classification of dynamic obstacles using the temporal information provided by videos0
Unsupervised part representation by Flow Capsules0
AC-VAE: Learning Semantic Representation with VAE for Adaptive Clustering0
Unsupervised Image Classification Through Time-Multiplexed Photonic Multi-Layer Spiking Convolutional Neural Network0
LatentGAN Autoencoder: Learning Disentangled Latent Distribution0
ContraCluster: Learning to Classify without Labels by Contrastive Self-Supervision and Prototype-Based Semi-Supervision0
Learning Latent Representations in Neural Networks for Clustering through Pseudo Supervision and Graph-based Activity Regularization0
Combining pretrained CNN feature extractors to enhance clustering of complex natural images0
Loss Function Entropy Regularization for Diverse Decision Boundaries0
Minimalistic Unsupervised Learning with the Sparse Manifold Transform0
MIX'EM: Unsupervised Image Classification using a Mixture of Embeddings0
Contrastive Knowledge Amalgamation for Unsupervised Image Classification0
Revisiting the Transferability of Supervised Pretraining: an MLP Perspective0
GUIDED MCMC FOR SPARSE BAYESIAN MODELS TO DETECT RARE EVENTS IN IMAGES SANS LABELED DATA0
Show:102550
← PrevPage 2 of 2Next →

No leaderboard results yet.