Unsupervised Few Shot Image Classification On 3

Metrics

Accuracy

Results

Performance results of various models on this benchmark

		Paper Title
BECLR	87.86	BECLR: Batch Enhanced Contrastive Few-Shot Learning
UniSiam	86.51	Self-Supervision Can Be a Good Few-Shot Learner
UBC-FSL	84.3	Shot in the Dark: Few-Shot Learning with No Base-Class Labels
PDA-Net	84.20	Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Images
HMS	75.85	Revisiting Unsupervised Meta-Learning via the Characteristics of Few-Shot Tasks
LF2CS	66.59	Unsupervised Few-Shot Image Classification by Learning Features into Clustering Space
SAMPTransfer (Conv4)	65.19	Self-Attention Message Passing for Contrastive Few-Shot Learning
PL-CFE	64.31	Rethinking Clustering-Based Pseudo-Labeling for Unsupervised Meta-Learning
CPNWCP	62.96	Contrastive Prototypical Network with Wasserstein Confidence Penalty
ArL	58.56	Rethinking Class Relations: Absolute-relative Supervised and Unsupervised Few-shot Learning
U-MlSo	57.53	Multi-level Second-order Few-shot Learning
ULDA	56.78	Diversity Helps: Unsupervised Few-shot Learning via Distribution Shift-based Data Augmentation

0 of 12 row(s) selected.