HyperAIHyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAIHyperAI

Few Shot Image Classification On Omniglot 5 1

Metrics

Accuracy

Results

Performance results of various models on this benchmark

Model Name
Accuracy
Paper TitleRepository
Prototypical Networks98.9%Prototypical Networks for Few-shot Learning-
GCR99.32Few-Shot Learning with Global Class Representations-
VAMPIRE98.52%Uncertainty in Model-Agnostic Meta-Learning using Variational Inference-
ConvNet with Memory Module98.6%Learning to Remember Rare Events-
Relation Net99.1%Learning to Compare: Relation Network for Few-Shot Learning-
Matching Nets98.5%Matching Networks for One Shot Learning-
DCN6-E99.63Decoder Choice Network for Meta-Learning-
Hyperbolic ProtoNet98.15%Hyperbolic Image Embeddings-
DCN499.5%Decoder Choice Network for Meta-Learning-
Reptile + Transduction97.12%On First-Order Meta-Learning Algorithms-
MAML++99.3%HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning-
MR-MAML94.1%Meta-Learning without Memorization-
adaCNN (DF)98.43%Rapid Adaptation with Conditionally Shifted Neurons-
TapNet99.49%TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning-
MC2+99.65%Meta-Curvature-
Neural Statistician98.1%Towards a Neural Statistician-
APL97.6%Adaptive Posterior Learning: few-shot learning with a surprise-based memory module-
MAML++99.33%How to train your MAML-
iMAML, Hessian-Free99.14%Meta-Learning with Implicit Gradients-
0 of 19 row(s) selected.
Few Shot Image Classification On Omniglot 5 1 | SOTA | HyperAI