Unsupervised Few Shot Image Classification On 2

Metrics

Accuracy

Results

Performance results of various models on this benchmark

		Paper Title
BECLR	81.69	BECLR: Batch Enhanced Contrastive Few-Shot Learning
UniSiam	69.60	Self-Supervision Can Be a Good Few-Shot Learner
PDA-Net	69.01	Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Images
UBC-FSL	68.0	Shot in the Dark: Few-Shot Learning with No Base-Class Labels
HMS	58.42	Revisiting Unsupervised Meta-Learning via the Characteristics of Few-Shot Tasks
LF2CS	53.16	Unsupervised Few-Shot Image Classification by Learning Features into Clustering Space
PL-CFE	49.51	Rethinking Clustering-Based Pseudo-Labeling for Unsupervised Meta-Learning
SAMPTransfer (Conv4)	49.10	Self-Attention Message Passing for Contrastive Few-Shot Learning
CPNWCP	45.00	Contrastive Prototypical Network with Wasserstein Confidence Penalty
ArL	43.68	Rethinking Class Relations: Absolute-relative Supervised and Unsupervised Few-shot Learning
U-MlSo	43.01	Multi-level Second-order Few-shot Learning
ULDA	41.77	Diversity Helps: Unsupervised Few-shot Learning via Distribution Shift-based Data Augmentation

0 of 12 row(s) selected.

Unsupervised Few Shot Image Classification On 2 | SOTA | HyperAI