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 2201–2225 of 3569 papers

TitleStatusHype
A Brief Survey of Associations Between Meta-Learning and General AI—0
Accelerating Distributed Online Meta-Learning via Multi-Agent Collaboration under Limited Communication—0
Accelerating Gradient-based Meta Learner—0
Accelerating Legacy Numerical Solvers by Non-intrusive Gradient-based Meta-solving—0
Accelerating Meta-Learning by Sharing Gradients—0
Accelerating Neural Self-Improvement via Bootstrapping—0
Principled Acceleration of Iterative Numerical Methods Using Machine Learning—0
Accelerating Online Reinforcement Learning via Model-Based Meta-Learning—0
ACE: Adapting to Changing Environments for Semantic Segmentation—0
A Chain-of-Thought Subspace Meta-Learning for Few-shot Image Captioning with Large Vision and Language Models—0
A Classification View on Meta Learning Bandits—0
A Closer Look at Prototype Classifier for Few-shot Image Classification—0
A CMDP-within-online framework for Meta-Safe Reinforcement Learning—0
Real-Time Edge Intelligence in the Making: A Collaborative Learning Framework via Federated Meta-Learning—0
A Communication and Computation Efficient Fully First-order Method for Decentralized Bilevel Optimization—0
A Comparative Analysis of Ensemble Classifiers: Case Studies in Genomics—0
A Comprehensive Overview and Survey of Recent Advances in Meta-Learning—0
A Comprehensive Review of Few-shot Action Recognition—0
A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends—0
A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities—0
A Survey on Curriculum Learning—0
A Comprehensive Survey of Dataset Distillation—0
A Comprehensive Sustainable Framework for Machine Learning and Artificial Intelligence—0
A Concise Review of Recent Few-shot Meta-learning Methods—0
A Primal-Dual Approach to Bilevel Optimization with Multiple Inner Minima—0
Show:102550
← PrevPage 89 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