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 1721–1730 of 3569 papers

TitleStatusHype
OmniPrint: A Configurable Printed Character SynthesizerCode1
A Meta-transfer Learning framework for Visually Grounded Compositional Concept Learning—0
AllWOZ: Towards Multilingual Task-Oriented Dialog Systems for All—0
Meta-CQG: A Meta-Learning Framework for Complex Question Generation over Knowledge Graph—0
Low Resource Style Transfer via Domain Adaptive Meta Learning—0
Improving both domain robustness and domain adaptability in machine translation—0
Meta Learning for Natural Language Processing: A Survey—0
Doing More with Less: Overcoming Data Scarcity for POI Recommendation via Cross-Region Transfer—0
Towards Sample-efficient Overparameterized Meta-learningCode0
Beyond Simple Meta-Learning: Multi-Purpose Models for Multi-Domain, Active and Continual Few-Shot Learning—0
Show:102550
← PrevPage 173 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