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 2531–2540 of 3569 papers

TitleStatusHype
How to distribute data across tasks for meta-learning?—0
Evolving parametrized Loss for Image Classification Learning on Small Datasets—0
Distance Metric-Based Learning with Interpolated Latent Features for Location Classification in Endoscopy Image and Video—0
Robust MAML: Prioritization task buffer with adaptive learning process for model-agnostic meta-learning—0
Meta-Learning for Planning: Automatic Synthesis of Sample Based Planners—0
Meta Learning for Multi-agent Communication—0
FEW-SHOTLEARNING WITH WEAK SUPERVISION—0
Learning where to learn—0
Meta-learning as Learning the Meta: A Videogame-Theoretic Perspective on\\ Learning to Learn—0
A Review on Semi-Supervised Relation Extraction—0
Show:102550
← PrevPage 254 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