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 1411–1420 of 3569 papers

TitleStatusHype
Label-template based Few-Shot Text Classification with Contrastive Learning—0
Language-Agnostic Meta-Learning for Low-Resource Text-to-Speech with Articulatory Features—0
Generalizable Representation Learning for Mixture Domain Face Anti-Spoofing—0
Improving Few-Shot Visual Classification with Unlabelled Examples—0
Generalizable Person Re-Identification by Domain-Invariant Mapping Network—0
Continuous Learning in a Hierarchical Multiscale Neural Network—0
Are encoders able to learn landmarkers for warm-starting of Hyperparameter Optimization?—0
Decoupled Pronunciation and Prosody Modeling in Meta-Learning-Based Multilingual Speech Synthesis—0
Age and Power Minimization via Meta-Deep Reinforcement Learning in UAV Networks—0
L2AE-D: Learning to Aggregate Embeddings for Few-shot Learning with Meta-level Dropout—0
Show:102550
← PrevPage 142 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