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 171–180 of 3569 papers

TitleStatusHype
Image Quality-aware Diagnosis via Meta-knowledge Co-embeddingCode1
GPT-PINN: Generative Pre-Trained Physics-Informed Neural Networks toward non-intrusive Meta-learning of parametric PDEsCode1
Architecture, Dataset and Model-Scale Agnostic Data-free Meta-LearningCode1
Learning Distortion Invariant Representation for Image Restoration from A Causality PerspectiveCode1
Structured State Space Models for In-Context Reinforcement LearningCode1
STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled TablesCode1
Unsupervised Meta-Learning via Few-shot Pseudo-supervised Contrastive LearningCode1
Meta Learning to Bridge Vision and Language Models for Multimodal Few-Shot LearningCode1
Incremental Few-Shot Object Detection via Simple Fine-Tuning ApproachCode1
Nystrom Method for Accurate and Scalable Implicit DifferentiationCode1
Show:102550
← PrevPage 18 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