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 191–200 of 3569 papers

TitleStatusHype
Contrastive Meta-Learning for Partially Observable Few-Shot LearningCode1
HyRSM++: Hybrid Relation Guided Temporal Set Matching for Few-shot Action RecognitionCode1
MetaFusion: Infrared and Visible Image Fusion via Meta-Feature Embedding From Object DetectionCode1
Deep Random Projector: Accelerated Deep Image PriorCode1
Generalizable Black-Box Adversarial Attack with Meta LearningCode1
Learning to Detect Noisy Labels Using Model-Based FeaturesCode1
OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of GeneralizationCode1
Are Deep Neural Networks SMARTer than Second Graders?Code1
Speeding Up Multi-Objective Hyperparameter Optimization by Task Similarity-Based Meta-Learning for the Tree-Structured Parzen EstimatorCode1
Transductive Linear Probing: A Novel Framework for Few-Shot Node ClassificationCode1
Show:102550
← PrevPage 20 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