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 491–500 of 3569 papers

TitleStatusHype
BOIL: Towards Representation Change for Few-shot LearningCode1
Domain Generalizer: A Few-shot Meta Learning Framework for Domain Generalization in Medical ImagingCode1
Offline Meta-Reinforcement Learning with Advantage WeightingCode1
Learning to Reason in Round-based Games: Multi-task Sequence Generation for Purchasing Decision Making in First-person ShootersCode1
ARCADe: A Rapid Continual Anomaly DetectorCode1
Offline Meta Learning of ExplorationCode1
Few-shot Classification via Adaptive AttentionCode1
One Model, Many Languages: Meta-learning for Multilingual Text-to-SpeechCode1
Learning to Purify Noisy Labels via Meta Soft Label CorrectorCode1
On Modulating the Gradient for Meta-LearningCode1
Show:102550
← PrevPage 50 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