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 271–280 of 3569 papers

TitleStatusHype
Learning to Adapt to Unseen Abnormal Activities under Weak SupervisionCode1
Cross-Domain Few-Shot Semantic SegmentationCode1
Predicting Multi-Antenna Frequency-Selective Channels via Meta-Learned Linear Filters based on Long-Short Term Channel DecompositionCode1
Pre-training to Match for Unified Low-shot Relation ExtractionCode1
Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot LearningCode1
MetAug: Contrastive Learning via Meta Feature AugmentationCode1
What Matters For Meta-Learning Vision Regression Tasks?Code1
FS-COCO: Towards Understanding of Freehand Sketches of Common Objects in ContextCode1
Contrastive Meta Learning with Behavior Multiplicity for RecommendationCode1
Learning to Generalize across Domains on Single Test SamplesCode1
Show:102550
← PrevPage 28 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