Unsupervised Few Shot Image Classification On

评估指标

Accuracy

评测结果

各个模型在此基准测试上的表现结果

		Paper Title	Repository
BECLR	80.57	BECLR: Batch Enhanced Contrastive Few-Shot Learning
Meta-DM+UniSiam	66.68	Meta-DM: Applications of Diffusion Models on Few-Shot Learning	-
UniSiam	65.55	Self-Supervision Can Be a Good Few-Shot Learner
PDA-Net	63.84	Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Images	-
SAMPTransfer (Conv4)	61.02	Self-Attention Message Passing for Contrastive Few-Shot Learning
Deep Laplacian Eigenmaps	59.47	Unsupervised Few-shot Learning via Deep Laplacian Eigenmaps	-
TrainProto	58.92	Trainable Class Prototypes for Few-Shot Learning	-
HMS	58.20	Revisiting Unsupervised Meta-Learning via the Characteristics of Few-Shot Tasks
UBC-FSL	57.1	Shot in the Dark: Few-Shot Learning with No Base-Class Labels	-
CSSL	54.17	Few-Shot Image Classification via Contrastive Self-Supervised Learning	-
CPNWCP	53.56	Contrastive Prototypical Network with Wasserstein Confidence Penalty	-
LF2CS	53.14	Unsupervised Few-Shot Image Classification by Learning Features into Clustering Space	-
PL-CFE	49.13	Rethinking Clustering-Based Pseudo-Labeling for Unsupervised Meta-Learning
C^3LR	47.92	Self-Supervised Class-Cognizant Few-Shot Classification
PsCo	46.70	Unsupervised Meta-Learning via Few-shot Pseudo-supervised Contrastive Learning
AmdimNet	46.13	Self-Supervised Learning For Few-Shot Image Classification
ProtoTransfer	45.67	Self-Supervised Prototypical Transfer Learning for Few-Shot Classification
CMVAE	44.27	CMVAE: Causal Meta VAE for Unsupervised Meta-Learning
Meta-SVEBM	43.38	Unsupervised Meta-Learning via Latent Space Energy-based Model of Symbol Vector Coupling	-
Meta-GMVAE	42.82	Meta-GMVAE: Mixture of Gaussian VAE for Unsupervised Meta-Learning	-

0 of 28 row(s) selected.