Home News Latest Papers Tutorials Datasets Wiki SOTA LLM Models GPU Leaderboard Events

English

Few Shot Image Classification On Omniglot 1 2

Metrics

Accuracy

Results

Performance results of various models on this benchmark

Model Name	Accuracy	Paper Title	Repository
iMAML, Hessian-Free	99.50	Meta-Learning with Implicit Gradients
Matching Nets	98.1	Matching Networks for One Shot Learning
Relation Net	99.6	Learning to Compare: Relation Network for Few-Shot Learning
MAML++	99.47	How to train your MAML
MAML	98.7	Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
adaCNN (DF)	98.42	Rapid Adaptation with Conditionally Shifted Neurons	-
VAMPIRE	98.43	Uncertainty in Model-Agnostic Meta-Learning using Variational Inference
DCN4	99.8%	Decoder Choice Network for Meta-Learning
Prototypical Networks	98.8	Prototypical Networks for Few-shot Learning
MT-net	99.5	Gradient-Based Meta-Learning with Learned Layerwise Metric and Subspace
ConvNet with Memory Module	98.4	Learning to Remember Rare Events
APL	97.9	Adaptive Posterior Learning: few-shot learning with a surprise-based memory module
MC2+	99.97	Meta-Curvature
Hyperbolic ProtoNet	99.0	Hyperbolic Image Embeddings
Neural Statistician	98.1	Towards a Neural Statistician
Reptile + Transduction	97.68	On First-Order Meta-Learning Algorithms
DCN6-E	99.92%	Decoder Choice Network for Meta-Learning

0 of 17 row(s) selected.