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 2981–2990 of 3569 papers

TitleStatusHype
Pre-training Text Representations as Meta Learning—0
Training few-shot classification via the perspective of minibatch and pretraining—0
Online Meta-Learning for Multi-Source and Semi-Supervised Domain Adaptation—0
Inferential Text Generation with Multiple Knowledge Sources and Meta-Learning—0
Meta-Learning for Few-Shot NMT Adaptation—0
Arbitrary Scale Super-Resolution for Brain MRI ImagesCode0
Sequential Learning for Domain Generalization—0
Leveraging Multi-Source Weak Social Supervision for Early Detection of Fake News—0
Guided Variational Autoencoder for Disentanglement Learning—0
Tracking by Instance Detection: A Meta-Learning Approach—0
Show:102550
← PrevPage 299 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