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 3051–3100 of 3569 papers

TitleStatusHype
Model Selection for Cross-Lingual TransferCode0
Learning to Self-Train for Semi-Supervised Few-Shot ClassificationCode0
Modular Adaptive Policy Selection for Multi-Task Imitation Learning through Task DivisionCode0
Episodic Multi-Task Learning with Heterogeneous Neural ProcessesCode0
Multi-task Meta Label Correction for Time Series PredictionCode0
Knowledge Distillation with Reptile Meta-Learning for Pretrained Language Model CompressionCode0
Episode-specific Fine-tuning for Metric-based Few-shot Learners with Optimization-based TrainingCode0
Joint Optimization of Class-Specific Training- and Test-Time Data Augmentation in SegmentationCode0
Centroids Matching: an efficient Continual Learning approach operating in the embedding spaceCode0
MetaCOVID: A Siamese neural network framework with contrastive loss for n-shot diagnosis of COVID-19 patientsCode0
Are Few-Shot Learning Benchmarks too Simple ? Solving them without Task Supervision at Test-TimeCode0
CellCLAT: Preserving Topology and Trimming Redundancy in Self-Supervised Cellular Contrastive LearningCode0
Assessor-Guided Learning for Continual EnvironmentsCode0
Structure-Enhanced Meta-Learning For Few-Shot Graph ClassificationCode0
Joint inference and input optimization in equilibrium networksCode0
More Flexible PAC-Bayesian Meta-Learning by Learning Learning AlgorithmsCode0
MVDG: A Unified Multi-view Framework for Domain GeneralizationCode0
Meta-Learned Modality-Weighted Knowledge Distillation for Robust Multi-Modal Learning with Missing DataCode0
Motley: Benchmarking Heterogeneity and Personalization in Federated LearningCode0
It HAS to be Subjective: Human Annotator Simulation via Zero-shot Density EstimationCode0
ST-SQL: Semi-Supervised Self-Training for Text-to-SQL via Column Specificity Meta-LearningCode0
Is Bayesian Model-Agnostic Meta Learning Better than Model-Agnostic Meta Learning, Provably?Code0
Enhanced Meta-Learning for Cross-lingual Named Entity Recognition with Minimal ResourcesCode0
Enabling Systematic Generalization in Abstract Spatial Reasoning through Meta-Learning for CompositionalityCode0
A Simple Neural Attentive Meta-LearnerCode0
Investigating Large Language Models for Complex Word Identification in Multilingual and Multidomain SetupsCode0
Inverse Learning with Extremely Sparse Feedback for RecommendationCode0
Multidimensional Belief Quantification for Label-Efficient Meta-LearningCode0
Remote Task-oriented Grasp Area Teaching By Non-Experts through Interactive Segmentation and Few-Shot LearningCode0
When Does Self-supervision Improve Few-shot Learning?Code0
Interval Bound Interpolation for Few-shot Learning with Few TasksCode0
Representation based meta-learning for few-shot spoken intent recognitionCode0
Style Interleaved Learning for Generalizable Person Re-identificationCode0
Meta Distribution Alignment for Generalizable Person Re-IdentificationCode0
Interpretable Meta-Measure for Model PerformanceCode0
Multi-Label Meta Weighting for Long-Tailed Dynamic Scene Graph GenerationCode0
INR-Arch: A Dataflow Architecture and Compiler for Arbitrary-Order Gradient Computations in Implicit Neural Representation ProcessingCode0
Incremental Meta-Learning via Episodic Replay Distillation for Few-Shot Image RecognitionCode0
Self-organization of action hierarchy and compositionality by reinforcement learning with recurrent neural networksCode0
Reproducibility Report: La-MAML: Look-ahead Meta Learning for Continual LearningCode0
Reproducing Meta-learning with differentiable closed-form solversCode0
Repurposing Pretrained Models for Robust Out-of-domain Few-Shot LearningCode0
Top-Related Meta-Learning Method for Few-Shot Object DetectionCode0
Style Variable and Irrelevant Learning for Generalizable Person Re-identificationCode0
Zero-shot task adaptation by homoiconic meta-mappingCode0
Incremental Few-Shot Learning with Attention Attractor NetworksCode0
Multi-Modal Fusion by Meta-InitializationCode0
Incorporating Test-Time Optimization into Training with Dual Networks for Human Mesh RecoveryCode0
In-Context Learning through the Bayesian PrismCode0
In-Context Learning for MIMO Equalization Using Transformer-Based Sequence ModelsCode0
Show:102550
← PrevPage 62 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