SOTAVerified

Meta-Learning

Meta-learning is a methodology considered with "learning to learn" machine learning algorithms.

( Image credit: Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 2961–2970 of 3569 papers

TitleStatusHype
Information-Theoretic Generalization Bounds for Meta-Learning and Applications—0
Predicting Scores of Medical Imaging Segmentation Methods with Meta-Learning—0
Safe Reinforcement Learning through Meta-learned Instincts—0
Generalized Reinforcement Meta Learning for Few-Shot Optimization—0
Watch, Try, Learn: Meta-Learning from Demonstrations and Rewards—0
Bayesian Meta Sampling for Fast Uncertainty AdaptationCode0
Addressing Catastrophic Forgetting in Few-Shot ProblemsCode0
Learning to Learn Morphological Inflection for Resource-Poor Languages—0
Meta-Learning for Few-Shot Land Cover Classification—0
MICK: A Meta-Learning Framework for Few-shot Relation Classification with Small Training Data—0
Show:102550
← PrevPage 297 of 357Next →
All datasetsML10MT50ML45OMNIGLOT - 1-Shot, 20-way

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MZ+ReconMeta-train success rate97.8—Unverified
2MZMeta-train success rate97.6—Unverified
3MAMLMeta-test success rate36—Unverified
4RL^2Meta-test success rate10—Unverified
5DnCMeta-test success rate5.4—Unverified
6PEARLMeta-test success rate0—Unverified
#ModelMetricClaimedVerifiedStatus
1SoftModuleAverage Success Rate60—Unverified
2Multi-task multi-head SACAverage Success Rate35.85—Unverified
3DisCorAverage Success Rate26—Unverified
4NDPAverage Success Rate11—Unverified
#ModelMetricClaimedVerifiedStatus
1MZ+ReconMeta-test success rate (zero-shot)18.5—Unverified
2MZMeta-test success rate (zero-shot)17.7—Unverified
#ModelMetricClaimedVerifiedStatus
1Metadrop% Test Accuracy95.75—Unverified