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 1826–1850 of 3569 papers

TitleStatusHype
Multimodal Emergent Fake News Detection via Meta Neural Process Networks—0
Multi-Modal Few-Shot Object Detection with Meta-Learning-Based Cross-Modal Prompting—0
Multi-modal Image and Radio Frequency Fusion for Optimizing Vehicle Positioning—0
Multimodality in Meta-Learning: A Comprehensive Survey—0
Multimodal Knowledge Learning for Named Entity Disambiguation—0
Multimodal Meta-Learning for Time Series Regression—0
Multi-Objective Meta Learning—0
Multi-Pair Text Style Transfer for Unbalanced Data via Task-Adaptive Meta-Learning—0
Multi-Pair Text Style Transfer on Unbalanced Data—0
Multiple Domain Experts Collaborative Learning: Multi-Source Domain Generalization For Person Re-Identification—0
Multi-Predict: Few Shot Predictors For Efficient Neural Architecture Search—0
Multi-resolution Tensor Learning for Large-Scale Spatial Data—0
Multi-source Meta Transfer for Low Resource Multiple-Choice Question Answering—0
Multi-source Unsupervised Domain Adaptation on Graphs with Transferability Modeling—0
Multi-step Estimation for Gradient-based Meta-learning—0
Multi-Subspace Structured Meta-Learning—0
Multi-Task and Transfer Learning for Federated Learning Applications—0
Multitask Learning with Single Gradient Step Update for Task Balancing—0
Multi-task Magnetic Resonance Imaging Reconstruction using Meta-learning—0
Multi-Teacher Multi-Objective Meta-Learning for Zero-Shot Hyperspectral Band Selection—0
MURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement Learning—0
MVP: Meta Visual Prompt Tuning for Few-Shot Remote Sensing Image Scene Classification—0
MxML: Mixture of Meta-Learners for Few-Shot Classification—0
Navigating the Trade-Off between Learning Efficacy and Processing Efficiency in Deep Neural Networks—0
Navigating the Trade-Off between Multi-Task Learning and Learning to Multitask in Deep Neural Networks—0
Show:102550
← PrevPage 74 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