Few Shot Image Classification On Tiered 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
CAML [Laion-2b]	98.8	Context-Aware Meta-Learning
TRIDENT	96.57	Transductive Decoupled Variational Inference for Few-Shot Classification
HCTransformers	91.72	Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learning
PEMnE-BMS*	91.09	Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning
PT+MAP	90.44	Leveraging the Feature Distribution in Transfer-based Few-Shot Learning
BAVARDAGE	90.41	Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification	-
FewTURE	89.96	Rethinking Generalization in Few-Shot Classification
TIM-GD	89.8	Transductive Information Maximization For Few-Shot Learning
EASY 3xResNet12 (transductive)	89.76	EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients
MetaQDA	89.56	Shallow Bayesian Meta Learning for Real-World Few-Shot Recognition
ASY ResNet12 (transductive)	89.26	EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients
ICI	89.00	Instance Credibility Inference for Few-Shot Learning
S2M2R	88.59	Charting the Right Manifold: Manifold Mixup for Few-shot Learning
EPNet	88.36	Embedding Propagation: Smoother Manifold for Few-Shot Classification
EASY 3xResNet12 (inductive)	88.33	EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients
LaplacianShot	87.93	Laplacian Regularized Few-Shot Learning	-
ASY ResNet12 (inductive)	87.86	EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients
Transductive CNAPS + FETI	87.7	Enhancing Few-Shot Image Classification with Unlabelled Examples
BD-CSPN + ESFR (WRN)	87.61	Unsupervised Embedding Adaptation via Early-Stage Feature Reconstruction for Few-Shot Classification
ESPT	87.49	ESPT: A Self-Supervised Episodic Spatial Pretext Task for Improving Few-Shot Learning

0 of 51 row(s) selected.