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 2791–2800 of 3569 papers

TitleStatusHype
Evaluating Data Influence in Meta Learning—0
Evaluating Deep Neural Network Ensembles by Majority Voting cum Meta-Learning scheme—0
Evaluating State of the Art, Forecasting Ensembles- and Meta-learning Strategies for Model Fusion—0
Ever Evolving Evaluator (EV3): Towards Flexible and Reliable Meta-Optimization for Knowledge Distillation—0
Everything Perturbed All at Once: Enabling Differentiable Graph Attacks—0
EvoFA: Evolvable Fast Adaptation for EEG Emotion Recognition—0
Evolution of Efficient Symbolic Communication Codes—0
Evolving Domain Generalization—0
Evolving Machine Learning: A Survey—0
Evolving parametrized Loss for Image Classification Learning on Small Datasets—0
Show:102550
← PrevPage 280 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