HyperAI
AccueilActualitésArticles de recherche récentsTutorielsEnsembles de donnéesWikiSOTAModèles LLMClassement GPUÉvénements
Recherche
À propos
HyperAI

Few Shot Image Classification On Meta Dataset

Métriques

Accuracy

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle
Accuracy
Paper TitleRepository
Transductive CNAPS70.32Enhancing Few-Shot Image Classification with Unlabelled Examples
Prototypical Networks60.573Prototypical Networks for Few-shot Learning
Matching Networks56.247Matching Networks for One Shot Learning
Simple CNAPS69.86Improved Few-Shot Visual Classification
TSP (ResNet18; applied on TA^2-Net)81.40Task-Specific Preconditioner for Cross-Domain Few-Shot Learning-
URT+MQDA74.3Shallow Bayesian Meta Learning for Real-World Few-Shot Recognition
fo-Proto-MAML63.428Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples
UpperCaSE-EfficientNetB076.1Contextual Squeeze-and-Excitation for Efficient Few-Shot Image Classification
TSA (ResNet18, URL, residual adapters, 84x84 image, shuffled data, scratch, MDL)78.07Cross-domain Few-shot Learning with Task-specific Adapters
k-NN54.319Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples
SUR70.72Selecting Relevant Features from a Multi-domain Representation for Few-shot Classification
SUR-pnf69.3Selecting Relevant Features from a Multi-domain Representation for Few-shot Classification
URL (ResNet18, 84x84 image, shuffled data, scratch, MDL)75.75Universal Representation Learning from Multiple Domains for Few-shot Classification
Invariance-Equivariance68.89Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning
Finetune58.758Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples
UpperCaSE-ResNet5074.9Contextual Squeeze-and-Excitation for Efficient Few-Shot Image Classification
fo-MAML57.024Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
URT72.15A Universal Representation Transformer Layer for Few-Shot Image Classification
CNAPs66.9Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes
P>M>F (P=DINO-ViT-base, M=ProtoNet)84.75Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference
0 of 22 row(s) selected.