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 2431–2440 of 3569 papers

TitleStatusHype
Learning to Optimize on SPD Manifolds—0
Learning to Profile: User Meta-Profile Network for Few-Shot Learning—0
Learning to Recommend via Meta Parameter Partition—0
Learning to Recover from Failures using Memory—0
Learning to Reinforcement Learn by Imitation—0
Learning to Remember from a Multi-Task Teacher—0
Learning to Retain while Acquiring: Combating Distribution-Shift in Adversarial Data-Free Knowledge Distillation—0
Learning to Sample: an Active Learning Framework—0
Learning to Sample and Aggregate: Few-shot Reasoning over Temporal Knowledge Graphs—0
Learning to segment anatomy and lesions from disparately labeled sources in brain MRI—0
Show:102550
← PrevPage 244 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