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 1791–1800 of 3569 papers

TitleStatusHype
MM-FSOD: Meta and metric integrated few-shot object detection—0
MMTL: The Meta Multi-Task Learning for Aspect Category Sentiment Analysis—0
MSD: Saliency-aware Knowledge Distillation for Multimodal Understanding—0
Modality-specific Distillation—0
Model-Agnostic Graph Regularization for Few-Shot Learning—0
Model-Agnostic Meta-Learning for EEG Motor Imagery Decoding in Brain-Computer-Interfacing—0
Model-Agnostic Meta-Learning for Fault Diagnosis of Induction Motors in Data-Scarce Environments with Varying Operating Conditions and Electric Drive Noise—0
Model-Agnostic Meta-Learning for Multilingual Hate Speech Detection—0
Model-Agnostic Meta-Learning for Multimodal Task Distributions—0
Model-Agnostic Meta-Learning for Natural Language Understanding Tasks in Finance—0
Show:102550
← PrevPage 180 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