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 3261–3270 of 3569 papers

TitleStatusHype
Meta-learning For Few-Shot Time Series Crop Type Classification: A Benchmark On The EuroCropsML DatasetCode0
One-Shot Visual Imitation Learning via Meta-LearningCode0
TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot LearningCode0
Targeted Data-driven Regularization for Out-of-Distribution GeneralizationCode0
Comparison of meta-learners for estimating multi-valued treatment heterogeneous effectsCode0
DiCE: The Infinitely Differentiable Monte-Carlo EstimatorCode0
Detecting Sockpuppetry on Wikipedia Using Meta-LearningCode0
Meta-learning Convolutional Neural Architectures for Multi-target Concrete Defect Classification with the COncrete DEfect BRidge IMage DatasetCode0
TART: Improved Few-shot Text Classification Using Task-Adaptive Reference TransformationCode0
Task2Vec: Task Embedding for Meta-LearningCode0
Show:102550
← PrevPage 327 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