Unsupervised Few Shot Image Classification On

Metrics

Accuracy

Results

Performance results of various models on this benchmark

Model Name	Accuracy	Paper Title	Repository
PsCo	46.70	Unsupervised Meta-Learning via Few-shot Pseudo-supervised Contrastive Learning
UBC-FSL	57.1	Shot in the Dark: Few-Shot Learning with No Base-Class Labels	-
BECLR	80.57	BECLR: Batch Enhanced Contrastive Few-Shot Learning
UniSiam	65.55	Self-Supervision Can Be a Good Few-Shot Learner
CPNWCP	53.56	Contrastive Prototypical Network with Wasserstein Confidence Penalty
ArL	41.08	Rethinking Class Relations: Absolute-relative Supervised and Unsupervised Few-shot Learning
Deep Laplacian Eigenmaps	59.47	Unsupervised Few-shot Learning via Deep Laplacian Eigenmaps	-
HMS	58.20	Revisiting Unsupervised Meta-Learning via the Characteristics of Few-Shot Tasks
CSSL	54.17	Few-Shot Image Classification via Contrastive Self-Supervised Learning	-
ULDA	40.71	Diversity Helps: Unsupervised Few-shot Learning via Distribution Shift-based Data Augmentation
AAL	37.67	Assume, Augment and Learn: Unsupervised Few-Shot Meta-Learning via Random Labels and Data Augmentation	-
AmdimNet	46.13	Self-Supervised Learning For Few-Shot Image Classification
U-MlSo+PN	41.09	Multi-level Second-order Few-shot Learning
TrainProto	58.92	Trainable Class Prototypes for Few-Shot Learning	-
LF2CS	53.14	Unsupervised Few-Shot Image Classification by Learning Features into Clustering Space
UMTRA	39.93	Unsupervised Meta-Learning For Few-Shot Image Classification	-
CACTU	39.90	Unsupervised Learning via Meta-Learning	-
Meta-DM+UniSiam	66.68	Meta-DM: Applications of Diffusion Models on Few-Shot Learning	-
ProtoTransfer	45.67	Self-Supervised Prototypical Transfer Learning for Few-Shot Classification
C^3LR	47.92	Self-Supervised Class-Cognizant Few-Shot Classification

0 of 28 row(s) selected.