Unsupervised Few Shot Image Classification On 1

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	87.82	BECLR: Batch Enhanced Contrastive Few-Shot Learning
Meta-DM+UniSiam	85.29	Meta-DM: Applications of Diffusion Models on Few-Shot Learning	-
UniSiam	83.40	Self-Supervision Can Be a Good Few-Shot Learner
PDA-Net	83.11	Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Images	-
Deep Laplacian Eigenmaps	78.79	Unsupervised Few-shot Learning via Deep Laplacian Eigenmaps	-
UBC-FSL	77.2	Shot in the Dark: Few-Shot Learning with No Base-Class Labels	-
HMS	75.77	Revisiting Unsupervised Meta-Learning via the Characteristics of Few-Shot Tasks
TrainProto	73.94	Trainable Class Prototypes for Few-Shot Learning	-
CPNWCP	73.21	Contrastive Prototypical Network with Wasserstein Confidence Penalty	-
SAMPTransfer (Conv4)	72.52	Self-Attention Message Passing for Contrastive Few-Shot Learning
AmdimNet	70.14	Self-Supervised Learning For Few-Shot Image Classification
CSSL	68.91	Few-Shot Image Classification via Contrastive Self-Supervised Learning	-
LF2CS	67.36	Unsupervised Few-Shot Image Classification by Learning Features into Clustering Space	-
C^3LR	64.81	Self-Supervised Class-Cognizant Few-Shot Classification
PsCo	63.26	Unsupervised Meta-Learning via Few-shot Pseudo-supervised Contrastive Learning
ProtoTransfer	62.99	Self-Supervised Prototypical Transfer Learning for Few-Shot Classification
PL-CFE	62.91	Rethinking Clustering-Based Pseudo-Labeling for Unsupervised Meta-Learning
CMVAE	58.95	CMVAE: Causal Meta VAE for Unsupervised Meta-Learning
Meta-SVEBM	58.03	Unsupervised Meta-Learning via Latent Space Energy-based Model of Symbol Vector Coupling	-
ArL	57.01	Rethinking Class Relations: Absolute-relative Supervised and Unsupervised Few-shot Learning

0 of 28 row(s) selected.