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 3051–3060 of 3569 papers

TitleStatusHype
Improving both domain robustness and domain adaptability in machine translation—0
Improving End-to-End Speech-to-Intent Classification with Reptile—0
Enhancing Few-Shot Image Classification with Unlabelled Examples—0
Improving Few-Shot Visual Classification with Unlabelled Examples—0
Improving Generalization of Meta-Learning With Inverted Regularization at Inner-Level—0
Improving Generalization via Meta-Learning on Hard Samples—0
Improving Meta-learning for Low-resource Text Classification and Generation via Memory Imitation—0
Improving the Generalization of Meta-learning on Unseen Domains via Adversarial Shift—0
Improving the performance of weak supervision searches using transfer and meta-learning—0
Improving the Reliability for Confidence Estimation—0
Show:102550
← PrevPage 306 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