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 1541–1550 of 3569 papers

TitleStatusHype
Directed Variational Cross-encoder Network for Few-shot Multi-image Co-segmentation—0
Learn2Hop: Learned Optimization on Rough Landscapes—0
Directional Domain Generalization—0
Learning to Generate Image Source-Agnostic Universal Adversarial Perturbations—0
Principled Acceleration of Iterative Numerical Methods Using Machine Learning—0
Function Contrastive Learning of Transferable Meta-Representations—0
Function Class Learning with Genetic Programming: Towards Explainable Meta Learning for Tumor Growth Functionals—0
Learning Abstract Task Representations—0
Learning to Identify Physical Laws of Hamiltonian Systems via Meta-Learning—0
Functionally Regionalized Knowledge Transfer for Low-resource Drug Discovery—0
Show:102550
← PrevPage 155 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