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 1341–1350 of 3569 papers

TitleStatusHype
How Fine-Tuning Allows for Effective Meta-Learning—0
How Important is the Train-Validation Split in Meta-Learning?—0
Generalized Visual Quality Assessment of GAN-Generated Face Images—0
Generalized Reinforcement Meta Learning for Few-Shot Optimization—0
Contrastive Learning is Just Meta-Learning—0
Generalized Few-Shot Semantic Segmentation: All You Need is Fine-Tuning—0
How to distribute data across tasks for meta-learning?—0
A statistical physics framework for optimal learning—0
Contrastive Knowledge-Augmented Meta-Learning for Few-Shot Classification—0
Adapting to the Unknown: Robust Meta-Learning for Zero-Shot Financial Time Series Forecasting—0
Show:102550
← PrevPage 135 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