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 2421–2430 of 3569 papers

TitleStatusHype
Person30K: A Dual-Meta Generalization Network for Person Re-Identification—0
Attacking Few-Shot Classifiers with Adversarial Support Poisoning—0
How Low Can We Go: Trading Memory for Error in Low-Precision TrainingCode0
MetaBalance: High-Performance Neural Networks for Class-Imbalanced Data—0
SPeCiaL: Self-Supervised Pretraining for Continual Learning—0
Contextualizing Meta-Learning via Learning to DecomposeCode0
Generative Conversational Networks—0
Learning Deep Morphological Networks with Neural Architecture SearchCode0
Domain Generalization on Medical Imaging Classification using Episodic Training with Task Augmentation—0
Knowledge Consolidation based Class Incremental Online Learning with Limited Data—0
Show:102550
← PrevPage 243 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