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 401–450 of 3569 papers

TitleStatusHype
Learn to Adapt for Generalized Zero-Shot Text ClassificationCode1
Automating Continual LearningCode1
Automating Outlier Detection via Meta-LearningCode1
LiST: Lite Prompted Self-training Makes Parameter-Efficient Few-shot LearnersCode1
LoRA Recycle: Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAsCode1
m^4Adapter: Multilingual Multi-Domain Adaptation for Machine Translation with a Meta-AdapterCode1
MaskSplit: Self-supervised Meta-learning for Few-shot Semantic SegmentationCode1
Massive Editing for Large Language Models via Meta LearningCode1
Chameleon: A Data-Efficient Generalist for Dense Visual Prediction in the WildCode1
MedFuncta: Modality-Agnostic Representations Based on Efficient Neural FieldsCode1
AutoPrognosis: Automated Clinical Prognostic Modeling via Bayesian Optimization with Structured Kernel LearningCode1
A Meta-Learning Approach for Graph Representation Learning in Multi-Task SettingsCode1
Memory Efficient Meta-Learning with Large ImagesCode1
MESA: Boost Ensemble Imbalanced Learning with MEta-SAmplerCode1
Cross-Market Product RecommendationCode1
MetaAvatar: Learning Animatable Clothed Human Models from Few Depth ImagesCode1
A Meta-Learning Approach for Training Explainable Graph Neural NetworksCode1
CURI: A Benchmark for Productive Concept Learning Under UncertaintyCode1
Data Augmentation for Meta-LearningCode1
Meta-Curriculum Learning for Domain Adaptation in Neural Machine TranslationCode1
AwesomeMeta+: A Mixed-Prototyping Meta-Learning System Supporting AI Application Design AnywhereCode1
MetaDelta: A Meta-Learning System for Few-shot Image ClassificationCode1
Meta-DMoE: Adapting to Domain Shift by Meta-Distillation from Mixture-of-ExpertsCode1
Bag of Tricks for Long-Tailed Visual Recognition with Deep Convolutional Neural NetworksCode1
Meta Dropout: Learning to Perturb Latent Features for GeneralizationCode1
MetaF2N: Blind Image Super-Resolution by Learning Efficient Model Adaptation from FacesCode1
BaMBNet: A Blur-aware Multi-branch Network for Defocus DeblurringCode1
Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target DataCode1
MetaGCD: Learning to Continually Learn in Generalized Category DiscoveryCode1
Meta-GMVAE: Mixture of Gaussian VAE for Unsupervised Meta-LearningCode1
Adaptive Multi-Teacher Knowledge Distillation with Meta-LearningCode1
Meta Internal LearningCode1
MetaKG: Meta-learning on Knowledge Graph for Cold-start RecommendationCode1
Meta-Learned Models of CognitionCode1
Meta-learning an Intermediate Representation for Few-shot Block-wise Prediction of Landslide SusceptibilityCode1
Delving Deep Into Many-to-Many Attention for Few-Shot Video Object SegmentationCode1
Meta-Learning based Degradation Representation for Blind Super-ResolutionCode1
Meta-Learning Based Knowledge Extrapolation for Knowledge Graphs in the Federated SettingCode1
Covariate Distribution Aware Meta-learningCode1
Meta-learning Extractors for Music Source SeparationCode1
Bayesian Model-Agnostic Meta-LearningCode1
Meta Learning for Few-Shot One-class ClassificationCode1
Meta-Learning for Short Utterance Speaker Recognition with Imbalance Length PairsCode1
Meta-learning framework with applications to zero-shot time-series forecastingCode1
Meta-Learning in Neural Networks: A SurveyCode1
Meta-Learning Loss Functions for Deep Neural NetworksCode1
Copolymer Informatics with Multi-Task Deep Neural NetworksCode1
Cross-Domain Few-Shot Classification via Adversarial Task AugmentationCode1
Meta-Learning to Communicate: Fast End-to-End Training for Fading ChannelsCode1
ContrastNet: A Contrastive Learning Framework for Few-Shot Text ClassificationCode1
Show:102550
← PrevPage 9 of 72Next →
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