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 611–620 of 3569 papers

TitleStatusHype
Curriculum-Meta Learning for Order-Robust Continual Relation ExtractionCode1
Learning to Adapt to Unseen Abnormal Activities under Weak SupervisionCode1
Learning to Compare: Relation Network for Few-Shot LearningCode1
Learning to Continually LearnCode1
Are Deep Neural Networks SMARTer than Second Graders?Code1
Continued Pretraining for Better Zero- and Few-Shot PromptabilityCode1
Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link PredictionCode1
Learning to Filter: Siamese Relation Network for Robust TrackingCode1
Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-IdentificationCode1
Evading Forensic Classifiers with Attribute-Conditioned Adversarial FacesCode1
Show:102550
← PrevPage 62 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