SOTAVerified

Unsupervised Few-Shot Image Classification

In contrast to (supervised) few-shot image classification, only the unlabeled dataset is available in the pre-training or meta-training stage for unsupervised few-shot image classification.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 28 papers

TitleStatusHype
BECLR: Batch Enhanced Contrastive Few-Shot LearningCode1
Contrastive Prototypical Network with Wasserstein Confidence PenaltyCode1
Unsupervised Few-Shot Image Classification by Learning Features into Clustering SpaceCode1
Self-Attention Message Passing for Contrastive Few-Shot LearningCode1
Self-Supervision Can Be a Good Few-Shot LearnerCode1
Meta-GMVAE: Mixture of Gaussian VAE for Unsupervised Meta-LearningCode1
Self-Supervised Prototypical Transfer Learning for Few-Shot ClassificationCode1
Diversity Helps: Unsupervised Few-shot Learning via Distribution Shift-based Data AugmentationCode1
Rethinking Class Relations: Absolute-relative Supervised and Unsupervised Few-shot LearningCode1
Meta-DM: Applications of Diffusion Models on Few-Shot Learning—0
Show:102550
← PrevPage 1 of 3Next →

No leaderboard results yet.