SOTAVerified

Unsupervised Few-Shot Learning

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 11–20 of 22 papers

TitleStatusHype
Revisiting Unsupervised Meta-Learning via the Characteristics of Few-Shot TasksCode0
Shot in the Dark: Few-Shot Learning with No Base-Class Labels—0
Few-Shot Image Classification via Contrastive Self-Supervised Learning—0
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
Unsupervised Few-shot Learning via Self-supervised Training—0
Program synthesis performance constrained by non-linear spatial relations in Synthetic Visual Reasoning TestCode0
Unsupervised Few Shot Learning via Self-supervised Training—0
Assume, Augment and Learn: Unsupervised Few-Shot Meta-Learning via Random Labels and Data Augmentation—0
Show:102550
← PrevPage 2 of 3Next →

No leaderboard results yet.