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 2676–2700 of 3569 papers

TitleStatusHype
Meta Learning MPC using Finite-Dimensional Gaussian Process Approximations—0
Offline Meta-Reinforcement Learning with Advantage WeightingCode1
Learning to Reason in Round-based Games: Multi-task Sequence Generation for Purchasing Decision Making in First-person ShootersCode1
Topic Adaptation and Prototype Encoding for Few-Shot Visual Storytelling—0
ARCADe: A Rapid Continual Anomaly DetectorCode1
Meta Feature Modulator for Long-tailed Recognition—0
Future Trends for Human-AI Collaboration: A Comprehensive Taxonomy of AI/AGI Using Multiple Intelligences and Learning Styles—0
Neural Complexity MeasuresCode0
Offline Meta Learning of ExplorationCode1
Few-shot Classification via Adaptive AttentionCode1
Data-driven Meta-set Based Fine-Grained Visual ClassificationCode0
A Neural-Symbolic Framework for Mental Simulation—0
Improving End-to-End Speech-to-Intent Classification with Reptile—0
Learning to Purify Noisy Labels via Meta Soft Label CorrectorCode1
One Model, Many Languages: Meta-learning for Multilingual Text-to-SpeechCode1
Targeted Data-driven Regularization for Out-of-Distribution GeneralizationCode0
Speech-driven Facial Animation using Cascaded GANs for Learning of Motion and Texture—0
Adaptive Variance Based Label Distribution Learning For Facial Age Estimation—0
On Modulating the Gradient for Meta-LearningCode1
Incremental Few-Shot Meta-Learning via Indirect Discriminant Alignment—0
Meta-DRN: Meta-Learning for 1-Shot Image Segmentation—0
Relation-aware Meta-learning for Market Segment Demand Prediction with Limited Records—0
Learning to Learn to Compress—0
Bayesian Optimization for Developmental Robotics with Meta-Learning by Parameters Bounds Reduction—0
Learning from Few Samples: A Survey—0
Show:102550
← PrevPage 108 of 143Next →
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