HyperAIHyperAI
StartseitePlattformDokumentationNeuigkeitenForschungsarbeitenTutorialsDatensätzeWikiSOTALLM-ModelleGPU-RanglisteVeranstaltungen
Suche
Über
HyperAIHyperAI

Command Palette

Search for a command to run...

Few Shot Image Classification On Meta Dataset

Metriken

Accuracy

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Paper TitleRepository
SMAT (DINO-VIT-Base-16-224)85.27Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Experts
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
TSP (ResNet18; applied on TA^2-Net)81.40Task-Specific Preconditioner for Cross-Domain Few-Shot Learning-
TSA (ResNet18, URL, residual adapters, 84x84 image, shuffled data, scratch, MDL)78.07Cross-domain Few-shot Learning with Task-specific Adapters
UpperCaSE-EfficientNetB076.1Contextual Squeeze-and-Excitation for Efficient Few-Shot Image Classification
URL (ResNet18, 84x84 image, shuffled data, scratch, MDL)75.75Universal Representation Learning from Multiple Domains for Few-shot Classification
UpperCaSE-ResNet5074.9Contextual Squeeze-and-Excitation for Efficient Few-Shot Image Classification
URT+MQDA74.3Shallow Bayesian Meta Learning for Real-World Few-Shot Recognition
URT72.15A Universal Representation Transformer Layer for Few-Shot Image Classification
SUR70.72Selecting Relevant Features from a Multi-domain Representation for Few-shot Classification
Transductive CNAPS70.32Enhancing Few-Shot Image Classification with Unlabelled Examples
Simple CNAPS69.86Improved Few-Shot Visual Classification
SUR-pnf69.3Selecting Relevant Features from a Multi-domain Representation for Few-shot Classification
Invariance-Equivariance68.89Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning
CNAPs66.9Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes
fo-Proto-MAML63.428Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples
Prototypical Networks60.573Prototypical Networks for Few-shot Learning
Finetune58.758Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples
fo-MAML57.024Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Matching Networks56.247Matching Networks for One Shot Learning
0 of 22 row(s) selected.