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 2501–2525 of 3569 papers

TitleStatusHype
Multilingual Transfer Learning for Code-Switched Language and Speech Neural Modeling—0
Contextual HyperNetworks for Novel Feature Adaptation—0
Meta-Learning for Fast Cross-Lingual Adaptation in Dependency ParsingCode0
Meta-Learning Bidirectional Update RulesCode0
Open Domain Generalization with Domain-Augmented Meta-Learning—0
Efficient time stepping for numerical integration using reinforcement learningCode0
Towards Enabling Meta-Learning from Target ModelsCode0
Few-Shot Meta-Learning on Point Cloud for Semantic Segmentation—0
Comparing Transfer and Meta Learning Approaches on a Unified Few-Shot Classification Benchmark—0
A Student-Teacher Architecture for Dialog Domain Adaptation under the Meta-Learning Setting—0
Thalamocortical contribution to solving credit assignment in neural systems—0
Fast-adapting and Privacy-preserving Federated Recommender System—0
Emotional RobBERT and Insensitive BERTje: Combining Transformers and Affect Lexica for Dutch Emotion Detection—0
Cross-Lingual Transfer with MAML on Trees—0
Keep Learning: Self-supervised Meta-learning for Learning from Inference—0
Conditional Meta-Learning of Linear Representations—0
Improved Meta-Learning Training for Speaker Verification—0
StyleMeUp: Towards Style-Agnostic Sketch-Based Image Retrieval—0
A Meta-Reinforcement Learning Approach to Process Control—0
Meta-Learned Invariant Risk Minimization—0
One to Many: Adaptive Instrument Segmentation via Meta Learning and Dynamic Online Adaptation in Robotic Surgical Video—0
Meta-Adversarial Inverse Reinforcement Learning for Decision-making Tasks—0
Using Meta-learning to Recommend Process Discovery MethodsCode0
Hyperspectral Image Super-Resolution in Arbitrary Input-Output Band Settings—0
Meta-learning of Pooling Layers for Character RecognitionCode0
Show:102550
← PrevPage 101 of 143Next →
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