HyperAI

Few Shot Image Classification On Fc100 5 Way

Métriques

Accuracy

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle
Accuracy
Paper TitleRepository
MetaOptNet-SVM+Task Aug49.77Task Augmentation by Rotating for Meta-Learning
Multi-Task Learning42.4Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation
FewTURE47.68Rethinking Generalization in Few-Shot Classification
SSFormers43.72Sparse Spatial Transformers for Few-Shot Learning
BAVARDAGE57.27Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification-
R2-D2+Task Aug51.35Task Augmentation by Rotating for Meta-Learning
MTL45.1Meta-Transfer Learning for Few-Shot Learning
MCRNet-RR40.7Complementing Representation Deficiency in Few-shot Image Classification: A Meta-Learning Approach
Invariance-Equivariance47.76Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning
EASY 2xResNet12 1/√2 (inductive)47.94EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients
ACC + Amphibian41.6Generalized Adaptation for Few-Shot Learning-
SKD46.5Self-supervised Knowledge Distillation for Few-shot Learning
EASY 3xResNet12 (transductive)54.13EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients
MSENet44.78Enhancing Few-Shot Image Classification through Learnable Multi-Scale Embedding and Attention Mechanisms
MetaOptNet-SVM-trainval47.2Meta-Learning with Differentiable Convex Optimization
pseudo-shots50.57Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks
HCTransformers48.27Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learning
MCRNet-SVM41Complementing Representation Deficiency in Few-shot Image Classification: A Meta-Learning Approach
ConstellationNets43.8Constellation Nets for Few-Shot Learning
EASY 3xResNet12 (inductive)48.07EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients
0 of 22 row(s) selected.