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 3261–3270 of 3569 papers

TitleStatusHype
Learning to Self-Train for Semi-Supervised Few-Shot ClassificationCode0
Sequential Scenario-Specific Meta Learner for Online RecommendationCode0
Incremental Few-Shot Learning for Pedestrian Attribute Recognition—0
Learning to Transfer: Unsupervised Meta Domain TranslationCode0
Team Fernando-Pessa at SemEval-2019 Task 4: Back to Basics in Hyperpartisan News Detection—0
Generalizable Person Re-Identification by Domain-Invariant Mapping Network—0
Task Agnostic Meta-Learning for Few-Shot Learning—0
Regression Networks for Meta-Learning Few-Shot ClassificationCode0
Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distribution TasksCode0
Meta-Learning Representations for Continual LearningCode0
Show:102550
← PrevPage 327 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