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 3381–3390 of 3569 papers

TitleStatusHype
Meta-free few-shot learning via representation learning with weight averaging—0
MetaFSCIL: A Meta-Learning Approach for Few-Shot Class Incremental Learning—0
MetaFuse: A Pre-trained Fusion Model for Human Pose Estimation—0
MetaGater: Fast Learning of Conditional Channel Gated Networks via Federated Meta-Learning—0
Meta-Gating Framework for Fast and Continuous Resource Optimization in Dynamic Wireless Environments—0
Meta-GCN: A Dynamically Weighted Loss Minimization Method for Dealing with the Data Imbalance in Graph Neural Networks—0
Meta Generative Attack on Person Reidentification—0
Meta Generative Flow Networks with Personalization for Task-Specific Adaptation—0
MetaGMT: Improving Actionable Interpretability of Graph Multilinear Networks via Meta-Learning Filtration—0
Meta Gradient Boosting Neural Networks—0
Show:102550
← PrevPage 339 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