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 2641–2650 of 3569 papers

TitleStatusHype
To Learn Effective Features: Understanding the Task-Specific Adaptation of MAML—0
B-SMALL: A Bayesian Neural Network approach to Sparse Model-Agnostic Meta-LearningCode0
Model agnostic meta-learning on trees—0
Connection-Adaptive Meta-Learning—0
TaskSet: A Dataset of Optimization TasksCode0
cross-modal knowledge enhancement mechanism for few-shot learning—0
Task Calibration for Distributional Uncertainty in Few-Shot Classification—0
Task-Aware Part Mining Network for Few-Shot Learning—0
Dataset Meta-Learning from Kernel-Ridge Regression—0
Meta-Learning in Reproducing Kernel Hilbert Space—0
Show:102550
← PrevPage 265 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