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 1451–1460 of 3569 papers

TitleStatusHype
Evolving parametrized Loss for Image Classification Learning on Small Datasets—0
Evolving Machine Learning: A Survey—0
Boosting Few-Shot Learning With Adaptive Margin Loss—0
Adaptive Self-training for Neural Sequence Labeling with Few Labels—0
Evolving Domain Generalization—0
Evolution of Efficient Symbolic Communication Codes—0
Boosting CLIP Adaptation for Image Quality Assessment via Meta-Prompt Learning and Gradient Regularization—0
A Moreau Envelope Approach for LQR Meta-Policy Estimation—0
EvoFA: Evolvable Fast Adaptation for EEG Emotion Recognition—0
Everything Perturbed All at Once: Enabling Differentiable Graph Attacks—0
Show:102550
← PrevPage 146 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