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 321–330 of 3569 papers

TitleStatusHype
AutoInit: Analytic Signal-Preserving Weight Initialization for Neural NetworksCode1
FewSAR: A Few-shot SAR Image Classification BenchmarkCode1
Few-Shot Class-Incremental Learning by Sampling Multi-Phase TasksCode1
Few Shot Dialogue State Tracking using Meta-learningCode1
A Simple Approach to Case-Based Reasoning in Knowledge BasesCode1
Few-shot Image Classification: Just Use a Library of Pre-trained Feature Extractors and a Simple ClassifierCode1
Few-Shot Learning with Class ImbalanceCode1
Few-shot Learning with LSSVM Base Learner and Transductive ModulesCode1
Few-Shot Named Entity Recognition: A Comprehensive StudyCode1
A Broader Study of Cross-Domain Few-Shot LearningCode1
Show:102550
← PrevPage 33 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