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 371–380 of 3569 papers

TitleStatusHype
Adaptive FSS: A Novel Few-Shot Segmentation Framework via Prototype EnhancementCode1
Difficulty-Net: Learning to Predict Difficulty for Long-Tailed RecognitionCode1
Learning to Generalize: Meta-Learning for Domain GeneralizationCode1
Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-IdentificationCode1
DIP: Unsupervised Dense In-Context Post-training of Visual RepresentationsCode1
DIMES: A Differentiable Meta Solver for Combinatorial Optimization ProblemsCode1
AutoDebias: Learning to Debias for RecommendationCode1
Direct Differentiable Augmentation SearchCode1
Few Shot Dialogue State Tracking using Meta-learningCode1
Few-Shot Learning with Class ImbalanceCode1
Show:102550
← PrevPage 38 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