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 2611–2620 of 3569 papers

TitleStatusHype
Meta-Regularization by Enforcing Mutual-ExclusivenessCode0
Contrastive Prototype Learning with Augmented Embeddings for Few-Shot Learning—0
Stress Testing of Meta-learning Approaches for Few-shot Learning—0
An Information-Theoretic Analysis of the Impact of Task Similarity on Meta-Learning—0
Meta-Reinforcement Learning for Adaptive Motor Control in Changing Robot Dynamics and Environments—0
Learning Abstract Task Representations—0
Robustness of Meta Matrix Factorization Against Strict Privacy ConstraintsCode0
Magnification Generalization for Histopathology Image EmbeddingCode0
Learning to Focus: Cascaded Feature Matching Network for Few-shot Image Recognition—0
A Brief Survey of Associations Between Meta-Learning and General AI—0
Show:102550
← PrevPage 262 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