Few Shot Image Classification On Mini 3

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
SgVA-CLIP	98.72	SgVA-CLIP: Semantic-guided Visual Adapting of Vision-Language Models for Few-shot Image Classification
CAML [Laion-2b]	98.6	Context-Aware Meta-Learning
P>M>F (P=DINO-ViT-base, M=ProtoNet)	98.4	Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference
TRIDENT	95.95	Transductive Decoupled Variational Inference for Few-Shot Classification
BAVARDAGE	91.65	Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification	-
PEMnE-BMS*(transductive)	91.53	Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning
Transductive CNAPS + FETI	91.5	Enhancing Few-Shot Image Classification with Unlabelled Examples
PT+MAP+SF+SOT (transductive)	91.34	The Self-Optimal-Transport Feature Transform
PT+MAP+SF+BPA (transductive)	91.34	The Balanced-Pairwise-Affinities Feature Transform
AmdimNet	90.98	Self-Supervised Learning For Few-Shot Image Classification
Simple CNAPS + FETI	90.3	Improved Few-Shot Visual Classification
HCTransformers	89.19	Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learning
Illumination Augmentation	89.14	Sill-Net: Feature Augmentation with Separated Illumination Representation
EASY 3xResNet12 (transductive)	89.14	EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients
PT+MAP	88.82	Leveraging the Feature Distribution in Transfer-based Few-Shot Learning
EASY 2xResNet12 1/√2 (transductive)	88.57	EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients
EPNet + SSL	88.05	Embedding Propagation: Smoother Manifold for Few-Shot Classification
EASY 3xResNet12 (inductive)	87.15	EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients
CPEA	87.06	Class-Aware Patch Embedding Adaptation for Few-Shot Image Classification	-
SemFew-Trans	86.49	Simple Semantic-Aided Few-Shot Learning

0 of 95 row(s) selected.

Command Palette

Few Shot Image Classification On Mini 3

评估指标

评测结果