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 3041–3050 of 3569 papers

TitleStatusHype
Compositional ADAM: An Adaptive Compositional Solver—0
Local Nonparametric Meta-LearningCode0
GradMix: Multi-source Transfer across Domains and Tasks—0
ML-misfit: Learning a robust misfit function for full-waveform inversion using machine learning—0
Analyzing Policy Distillation on Multi-Task Learning and Meta-Reinforcement Learning in Meta-World—0
Task Augmentation by Rotating for Meta-LearningCode0
Few-Shot Learning as Domain Adaptation: Algorithm and Analysis—0
Revisiting Meta-Learning as Supervised Learning—0
Extreme Algorithm Selection With Dyadic Feature RepresentationCode0
Optimized Generic Feature Learning for Few-shot Classification across Domains—0
Show:102550
← PrevPage 305 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