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 3181–3190 of 3569 papers

TitleStatusHype
Learning to Adapt to Online Streams with Distribution Shifts—0
Learning to Adapt to Semantic Shift—0
Learning to Adapt via Latent Domains for Adaptive Semantic Segmentation—0
Learning to Augment via Implicit Differentiation for Domain Generalization—0
Learning to Bound the Multi-class Bayes Error—0
Learning to Classify Intents and Slot Labels Given a Handful of Examples—0
Is Nash Equilibrium Approximator Learnable?—0
Learning to Cope with Adversarial Attacks—0
Learning to Focus: Cascaded Feature Matching Network for Few-shot Image Recognition—0
Learning to Generalize to Unseen Tasks with Bilevel Optimization—0
Show:102550
← PrevPage 319 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