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 3021–3030 of 3569 papers

TitleStatusHype
An Ensemble of Epoch-wise Empirical Bayes for Few-shot LearningCode0
MetaAge: Meta-Learning Personalized Age EstimatorsCode0
Layer-compensated Pruning for Resource-constrained Convolutional Neural NetworksCode0
Latent Task-Specific Graph Network SimulatorsCode0
Evaluating Fast Adaptability of Neural Networks for Brain-Computer InterfaceCode0
Regularized Fine-grained Meta Face Anti-spoofingCode0
Closed-form Sample Probing for Learning Generative Models in Zero-shot LearningCode0
3FM: Multi-modal Meta-learning for Federated TasksCode0
MetaASSIST: Robust Dialogue State Tracking with Meta LearningCode0
Unsupervised Learning for Combinatorial Optimization Needs Meta-LearningCode0
Show:102550
← PrevPage 303 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