Few Shot Image Classification On Cifar Fs 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

		Paper Title	Repository
CAML [Laion-2b]	93.5	Context-Aware Meta-Learning
PT+MAP+SF+SOT (transductive)	92.83	The Self-Optimal-Transport Feature Transform
PT+MAP+SF+BPA (transductive)	92.83	The Balanced-Pairwise-Affinities Feature Transform
P>M>F (P=DINO-ViT-base, M=ProtoNet)	92.2	Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference
PEMnE-BMS*	91.86	Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning
Illumination Augmentation	91.09	Sill-Net: Feature Augmentation with Separated Illumination Representation
LST+MAP	90.73	Transfer learning based few-shot classification using optimal transport mapping from preprocessed latent space of backbone neural network
PT+MAP	90.68	Leveraging the Feature Distribution in Transfer-based Few-Shot Learning
BAVARDAGE	90.63	Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification	-
HCTransformers	90.50	Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learning
EASY 3xResNet12 (transductive)	90.47	EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients
EASY 2xResNet12 1/√2 (transductive)	90.2	EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients
Invariance-Equivariance	89.74	Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning
ACC + Amphibian	89.3	Generalized Adaptation for Few-Shot Learning	-
pseudo-shots	89.12	Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks
EASY 3xResNet12 (inductive)	89.0	EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients
FewTURE	88.90	Rethinking Generalization in Few-Shot Classification
SKD	88.9	Self-supervised Knowledge Distillation for Few-shot Learning
MetaQDA	88.79	Shallow Bayesian Meta Learning for Real-World Few-Shot Recognition
MetaOptNet-SVM+Task Aug	88.38	Task Augmentation by Rotating for Meta-Learning

0 of 39 row(s) selected.

Command Palette

Few Shot Image Classification On Cifar Fs 5 1

评估指标

评测结果