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 1981–1990 of 3569 papers

TitleStatusHype
Population-Based Evolution Optimizes a Meta-Learning Objective—0
Portrait Neural Radiance Fields from a Single Image—0
Practical Conditional Neural Processes Via Tractable Dependent Predictions—0
Practical Conditional Neural Process Via Tractable Dependent Predictions—0
Predicting Scores of Medical Imaging Segmentation Methods with Meta-Learning—0
Prepare for Trouble and Make it Double. Supervised and Unsupervised Stacking for AnomalyBased Intrusion Detection—0
Preparing for Black Swans: The Antifragility Imperative for Machine Learning—0
Pre-Trained Language Transformers are Universal Image Classifiers—0
Pre-training with Meta Learning for Chinese Word Segmentation—0
Pre-Training and Personalized Fine-Tuning via Over-the-Air Federated Meta-Learning: Convergence-Generalization Trade-Offs—0
Show:102550
← PrevPage 199 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