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 71–80 of 3569 papers

TitleStatusHype
Bitwidth-Adaptive Quantization-Aware Neural Network Training: A Meta-Learning ApproachCode1
BaMBNet: A Blur-aware Multi-branch Network for Defocus DeblurringCode1
Alchemy: A benchmark and analysis toolkit for meta-reinforcement learning agentsCode1
Bayesian Model-Agnostic Meta-LearningCode1
BlackGoose Rimer: Harnessing RWKV-7 as a Simple yet Superior Replacement for Transformers in Large-Scale Time Series ModelingCode1
Boosting Few-Shot Classification with View-Learnable Contrastive LearningCode1
Consolidated learning -- a domain-specific model-free optimization strategy with examples for XGBoost and MIMIC-IVCode1
Automating Outlier Detection via Meta-LearningCode1
Automating Continual LearningCode1
AutoPrognosis: Automated Clinical Prognostic Modeling via Bayesian Optimization with Structured Kernel LearningCode1
Show:102550
← PrevPage 8 of 357Next →
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