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 181–190 of 3569 papers

TitleStatusHype
Dynamic Distillation Network for Cross-Domain Few-Shot Recognition with Unlabeled DataCode1
Dynamic Relevance Learning for Few-Shot Object DetectionCode1
AutoPrognosis: Automated Clinical Prognostic Modeling via Bayesian Optimization with Structured Kernel LearningCode1
CURI: A Benchmark for Productive Concept Learning Under UncertaintyCode1
Adaptive FSS: A Novel Few-Shot Segmentation Framework via Prototype EnhancementCode1
Efficient Domain Generalization via Common-Specific Low-Rank DecompositionCode1
A Simple Approach to Case-Based Reasoning in Knowledge BasesCode1
AwesomeMeta+: A Mixed-Prototyping Meta-Learning System Supporting AI Application Design AnywhereCode1
On the Convergence Theory for Hessian-Free Bilevel AlgorithmsCode1
Curriculum-Meta Learning for Order-Robust Continual Relation ExtractionCode1
Show:102550
← PrevPage 19 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