Few Shot Image Classification On Cub 200 5 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

模型名称	Accuracy	Paper Title	Repository
feat (ProtoNet)	68.65	Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions
EASY 4xResNet12 (transductive)	90.5	EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients
EASY 3xResNet12 (inductive)	78.56	EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients
TIM-GD	82.2%	Transductive Information Maximization For Few-Shot Learning
HyperShot	66.13	HyperShot: Few-Shot Learning by Kernel HyperNetworks
PT+MAP+SF+BPA (transductive)	95.80	The Balanced-Pairwise-Affinities Feature Transform
DN4-DA (k=1)	53.15	Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learning
EASY 3xResNet12 (transductive)	90.56	EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients
PT+MAP+SF+SOT (transductive)	95.80	The Self-Optimal-Transport Feature Transform
Transfer+SGC	88.35%	Graph-based Interpolation of Feature Vectors for Accurate Few-Shot Classification	-
Relation Net	50.44	Learning to Compare: Relation Network for Few-Shot Learning
PT+MAP+SF (transductive)	95.48	Few-Shot Learning by Integrating Spatial and Frequency Representation
CAML [Laion-2b]	95.8	Context-Aware Meta-Learning	-
MergedNet-Max	75.34	MergedNET: A simple approach for one-shot learning in siamese networks based on similarity layers
PEMnE-BMS*	94.78	Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning
LaplacianShot	80.96	Laplacian Regularized Few-Shot Learning
High-End MAML++	67.48	Learning to learn via Self-Critique
RS-FSL	65.66	Rich Semantics Improve Few-shot Learning	-
S2M2R	80.68	Charting the Right Manifold: Manifold Mixup for Few-shot Learning
Self-Critique and Adapt + High-End MAML++	70.46	Learning to learn via Self-Critique

0 of 36 row(s) selected.