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 2471–2480 of 3569 papers

TitleStatusHype
DRILL: Dynamic Representations for Imbalanced Lifelong LearningCode0
HetMAML: Task-Heterogeneous Model-Agnostic Meta-Learning for Few-Shot Learning Across Modalities—0
Deep Metric Learning for Few-Shot Image Classification: A Review of Recent Developments—0
Meta Auxiliary Learning for Facial Action Unit Detection—0
Meta-Inductive Node Classification across Graphs—0
Exploring the Similarity of Representations in Model-Agnostic Meta-LearningCode0
Transfer-Meta Framework for Cross-domain Recommendation to Cold-Start Users—0
Evaluating Deep Neural Network Ensembles by Majority Voting cum Meta-Learning scheme—0
MetaKernel: Learning Variational Random Features with Limited LabelsCode0
Long Short-Term Temporal Meta-learning in Online Recommendation—0
Show:102550
← PrevPage 248 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