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 121–130 of 3569 papers

TitleStatusHype
Neural Relational Inference with Fast Modular Meta-learningCode1
Domain Adaptive Few-Shot Open-Set LearningCode1
Graph Contrastive Learning Meets Graph Meta Learning: A Unified Method for Few-shot Node TasksCode1
MetaF2N: Blind Image Super-Resolution by Learning Efficient Model Adaptation from FacesCode1
Fine-grained Recognition with Learnable Semantic Data AugmentationCode1
Self-Sampling Meta SAM: Enhancing Few-shot Medical Image Segmentation with Meta-LearningCode1
MetaWeather: Few-Shot Weather-Degraded Image RestorationCode1
MetaGCD: Learning to Continually Learn in Generalized Category DiscoveryCode1
Generalizable Decision Boundaries: Dualistic Meta-Learning for Open Set Domain GeneralizationCode1
Privacy-preserving Few-shot Traffic Detection against Advanced Persistent Threats via Federated Meta LearningCode1
Show:102550
← PrevPage 13 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