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 1–28 of 28 papers

TitleStatusHype
Self-Supervision Can Be a Good Few-Shot LearnerCode1
Rethinking Class Relations: Absolute-relative Supervised and Unsupervised Few-shot LearningCode1
Self-Supervised Prototypical Transfer Learning for Few-Shot ClassificationCode1
Contrastive Prototypical Network with Wasserstein Confidence PenaltyCode1
Self-Attention Message Passing for Contrastive Few-Shot LearningCode1
Unsupervised Few-Shot Image Classification by Learning Features into Clustering SpaceCode1
Diversity Helps: Unsupervised Few-shot Learning via Distribution Shift-based Data AugmentationCode1
BECLR: Batch Enhanced Contrastive Few-Shot LearningCode1
Meta-GMVAE: Mixture of Gaussian VAE for Unsupervised Meta-LearningCode1
Self-Supervised Class-Cognizant Few-Shot ClassificationCode0
CMVAE: Causal Meta VAE for Unsupervised Meta-LearningCode0
Multi-level Second-order Few-shot LearningCode0
Rethinking Clustering-Based Pseudo-Labeling for Unsupervised Meta-LearningCode0
Revisiting Unsupervised Meta-Learning via the Characteristics of Few-Shot TasksCode0
Self-Supervised Learning For Few-Shot Image ClassificationCode0
Unsupervised Meta-Learning via Latent Space Energy-based Model of Symbol Vector Coupling—0
Few-Shot Image Classification via Contrastive Self-Supervised Learning—0
Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Images—0
Invariant and consistent: Unsupervised representation learning for few-shot visual recognition—0
Meta-DM: Applications of Diffusion Models on Few-Shot Learning—0
Shot in the Dark: Few-Shot Learning with No Base-Class Labels—0
Trainable Class Prototypes for Few-Shot Learning—0
Unsupervised Few-shot Learning via Deep Laplacian Eigenmaps—0
Unsupervised Few-shot Learning via Self-supervised Training—0
Unsupervised Learning via Meta-Learning—0
Unsupervised Meta-Learning For Few-Shot Image Classification—0
Unsupervised Meta-Learning through Latent-Space Interpolation in Generative Models—0
Assume, Augment and Learn: Unsupervised Few-Shot Meta-Learning via Random Labels and Data Augmentation—0
Show:102550

No leaderboard results yet.