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 31–40 of 3569 papers

TitleStatusHype
Discovering Evolution Strategies via Meta-Black-Box OptimizationCode2
Meta-DETR: Image-Level Few-Shot Detection with Inter-Class Correlation ExploitationCode2
Learning Deep Time-index Models for Time Series ForecastingCode2
Towards Learning Universal Hyperparameter Optimizers with TransformersCode2
DevFormer: A Symmetric Transformer for Context-Aware Device PlacementCode2
Neural-Fly Enables Rapid Learning for Agile Flight in Strong WindsCode2
Decomposed Meta-Learning for Few-Shot Named Entity RecognitionCode2
Learning What Not to Segment: A New Perspective on Few-Shot SegmentationCode2
Tutorial on amortized optimizationCode2
TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series DataCode2
Show:102550
← PrevPage 4 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