HyperAI超神经
首页资讯最新论文教程数据集百科SOTALLM 模型天梯GPU 天梯顶会
全站搜索
关于
HyperAI超神经

Few Shot Image Classification On Tiered

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

模型名称
Accuracy
Paper TitleRepository
TapNet63.08TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning
DiffKendall (Meta-Baseline, ResNet-12)70.76DiffKendall: A Novel Approach for Few-Shot Learning with Differentiable Kendall's Rank Correlation
CAML [Laion-2b]96.8Context-Aware Meta-Learning-
HCTransformers79.67Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learning
Adaptive Subspace Network68.44Adaptive Subspaces for Few-Shot Learning
LST77.7Learning to Self-Train for Semi-Supervised Few-Shot Classification
BD-CSPN + ESFR (ResNet-18)80.13Unsupervised Embedding Adaptation via Early-Stage Feature Reconstruction for Few-Shot Classification
RENet71.61Relational Embedding for Few-Shot Classification
ASY ResNet12 (transductive)83.98EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients
MTUNet+WRN62.42Match Them Up: Visually Explainable Few-shot Image Classification
TIM-GD82.1Transductive Information Maximization For Few-Shot Learning
EASY 3xResNet12 (inductive)74.71EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients
GML (ResNet-12)69.61Geometric Mean Improves Loss For Few-Shot Learning-
ASY ResNet12 (ours)74.31EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients
SImPa70.82PAC-Bayes meta-learning with implicit task-specific posteriors
Deep Comparison Network68.83RelationNet2: Deep Comparison Columns for Few-Shot Learning
AM3-TADAM69.08Adaptive Cross-Modal Few-Shot Learning
Transductive CNAPS65.9Enhancing Few-Shot Image Classification with Unlabelled Examples
Simple CNAPS + FETI71.4Improved Few-Shot Visual Classification
BAVARDAGE85.20Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification-
0 of 49 row(s) selected.