Few Shot Image Classification On Cifar Fs 5

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
PT+MAP+SF+SOT (transductive)	89.94	The Self-Optimal-Transport Feature Transform
PT+MAP+SF+BPA (transductive)	89.94	The Balanced-Pairwise-Affinities Feature Transform
PEMnE-BMS*	88.44	Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning
LST+MAP	87.79	Transfer learning based few-shot classification using optimal transport mapping from preprocessed latent space of backbone neural network
Illumination Augmentation	87.73	Sill-Net: Feature Augmentation with Separated Illumination Representation
PT+MAP	87.69	Leveraging the Feature Distribution in Transfer-based Few-Shot Learning
BAVARDAGE	87.35	Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification	-
EASY 3xResNet12 (transductive)	87.16	EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients
EASY 2xResNet12 1/√2 (transductive)	86.99	EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients
P>M>F (P=DINO-ViT-base, M=ProtoNet)	84.3	Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference
CAML [Laion-2b]	83.3	Context-Aware Meta-Learning
pseudo-shots	81.87	Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks
SIB	80.0	Empirical Bayes Transductive Meta-Learning with Synthetic Gradients
HCTransformers	78.89	Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learning
Adaptive Subspace Network	78	Adaptive Subspaces for Few-Shot Learning	-
Invariance-Equivariance	77.87	Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning
FewTURE	77.76	Rethinking Generalization in Few-Shot Classification
R2-D2+Task Aug	77.66	Task Augmentation by Rotating for Meta-Learning
SKD	76.9	Self-supervised Knowledge Distillation for Few-shot Learning
MetaOptNet-SVM+Task Aug	76.75	Task Augmentation by Rotating for Meta-Learning

0 of 38 row(s) selected.

Command Palette

Few Shot Image Classification On Cifar Fs 5

评估指标

评测结果