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

Showing 451475 of 3569 papers

TitleStatusHype
Few-Shot Microscopy Image Cell SegmentationCode1
Few-shot Learning with LSSVM Base Learner and Transductive ModulesCode1
Few-shot Network Anomaly Detection via Cross-network Meta-learningCode1
Few-Shot Named Entity Recognition: A Comprehensive StudyCode1
GenSDF: Two-Stage Learning of Generalizable Signed Distance FunctionsCode1
Few-shot Object Detection via Feature ReweightingCode1
Few-Shot Open-Set Recognition using Meta-LearningCode1
Few-Shot One-Class Classification via Meta-LearningCode1
Beyond the Prototype: Divide-and-conquer Proxies for Few-shot SegmentationCode1
Few-shot Relational Reasoning via Connection Subgraph PretrainingCode1
Few-shot Scene-adaptive Anomaly DetectionCode1
Few-Shot Scene Adaptive Crowd Counting Using Meta-LearningCode1
Efficient Domain Generalization via Common-Specific Low-Rank DecompositionCode1
Induction Networks for Few-Shot Text ClassificationCode1
Few-shot Visual Relationship Co-localizationCode1
MetaVIM: Meta Variationally Intrinsic Motivated Reinforcement Learning for Decentralized Traffic Signal ControlCode1
Bilevel Optimization with a Lower-level Contraction: Optimal Sample Complexity without Warm-startCode1
A Brain Graph Foundation Model: Pre-Training and Prompt-Tuning for Any Atlas and DisorderCode1
Geometric Dataset Distances via Optimal TransportCode1
MetaXL: Meta Representation Transformation for Low-resource Cross-lingual LearningCode1
Bitwidth-Adaptive Quantization-Aware Neural Network Training: A Meta-Learning ApproachCode1
FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image ClassificationCode1
First-Explore, then Exploit: Meta-Learning to Solve Hard Exploration-Exploitation Trade-OffsCode1
Model-Agnostic Meta-Learning for Fast Adaptation of Deep NetworksCode1
Boosting Few-Shot Classification with View-Learnable Contrastive LearningCode1
Show:102550
← PrevPage 19 of 143Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MZ+ReconMeta-train success rate97.8Unverified
2MZMeta-train success rate97.6Unverified
3MAMLMeta-test success rate36Unverified
4RL^2Meta-test success rate10Unverified
5DnCMeta-test success rate5.4Unverified
6PEARLMeta-test success rate0Unverified
#ModelMetricClaimedVerifiedStatus
1SoftModuleAverage Success Rate60Unverified
2Multi-task multi-head SACAverage Success Rate35.85Unverified
3DisCorAverage Success Rate26Unverified
4NDPAverage Success Rate11Unverified
#ModelMetricClaimedVerifiedStatus
1MZ+ReconMeta-test success rate (zero-shot)18.5Unverified
2MZMeta-test success rate (zero-shot)17.7Unverified
#ModelMetricClaimedVerifiedStatus
1Metadrop% Test Accuracy95.75Unverified