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 421–430 of 3569 papers

TitleStatusHype
AwesomeMeta+: A Mixed-Prototyping Meta-Learning System Supporting AI Application Design AnywhereCode1
Meta-Learning Dynamics Forecasting Using Task InferenceCode1
Exploration in Approximate Hyper-State Space for Meta Reinforcement LearningCode1
Bag of Tricks for Long-Tailed Visual Recognition with Deep Convolutional Neural NetworksCode1
Exploring Task Difficulty for Few-Shot Relation ExtractionCode1
BERT Learns to Teach: Knowledge Distillation with Meta LearningCode1
BaMBNet: A Blur-aware Multi-branch Network for Defocus DeblurringCode1
Exploring Effective Factors for Improving Visual In-Context LearningCode1
Meta-Learning Initializations for Low-Resource Drug DiscoveryCode1
First-Explore, then Exploit: Meta-Learning to Solve Hard Exploration-Exploitation Trade-OffsCode1
Show:102550
← PrevPage 43 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