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 451–460 of 3569 papers

TitleStatusHype
Few-Shot Learning with a Strong TeacherCode1
A Survey of Few-Shot Learning on Graphs: from Meta-Learning to Pre-Training and Prompt LearningCode1
Meta-SAGE: Scale Meta-Learning Scheduled Adaptation with Guided Exploration for Mitigating Scale Shift on Combinatorial OptimizationCode1
Few-Shot Learning with Class ImbalanceCode1
Few-shot Network Anomaly Detection via Cross-network Meta-learningCode1
Few-Shot Named Entity Recognition: A Comprehensive StudyCode1
Few-Shot Object Detection and Viewpoint Estimation for Objects in the WildCode1
Few-Shot Open-Set Recognition using Meta-LearningCode1
Beyond the Prototype: Divide-and-conquer Proxies for Few-shot SegmentationCode1
Blind Super-Resolution via Meta-learning and Markov Chain Monte Carlo SimulationCode1
Show:102550
← PrevPage 46 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