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 3311–3320 of 3569 papers

TitleStatusHype
MDFL: A UNIFIED FRAMEWORK WITH META-DROPOUT FOR FEW-SHOT LEARNING—0
Measuring few-shot extrapolation with program induction—0
Meet JEANIE: a Similarity Measure for 3D Skeleton Sequences via Temporal-Viewpoint Alignment—0
MELR: Meta-Learning via Modeling Episode-Level Relationships for Few-Shot Learning—0
Memory-Reduced Meta-Learning with Guaranteed Convergence—0
MERMAIDE: Learning to Align Learners using Model-Based Meta-Learning—0
MESA: Offline Meta-RL for Safe Adaptation and Fault Tolerance—0
Single-View 3D Object Reconstruction from Shape Priors in Memory—0
Meta-Active Learning for Node Response Prediction in Graphs—0
Meta-active Learning in Probabilistically-Safe Optimization—0
Show:102550
← PrevPage 332 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