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 3451–3460 of 3569 papers

TitleStatusHype
Guided evolutionary strategies: Augmenting random search with surrogate gradientsCode0
Attention-based Few-Shot Person Re-identification Using Meta Learning—0
Learning to Update for Object Tracking with Recurrent Meta-learner—0
Meta-learning: searching in the model space—0
Far-HO: A Bilevel Programming Package for Hyperparameter Optimization and Meta-LearningCode0
Bilevel Programming for Hyperparameter Optimization and Meta-Learning—0
Meta-Learning for Stochastic Gradient MCMCCode0
Unsupervised Meta-Learning for Reinforcement Learning—0
Meta-Learning Transferable Active Learning Policies by Deep Reinforcement Learning—0
Auto-Meta: Automated Gradient Based Meta Learner Search—0
Show:102550
← PrevPage 346 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