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 2701–2710 of 3569 papers

TitleStatusHype
Unsupervised Alternating Optimization for Blind Hyperspectral Imagery Super-resolution—0
SB-MTL: Score-based Meta Transfer-Learning for Cross-Domain Few-Shot Learning—0
Meta-KD: A Meta Knowledge Distillation Framework for Language Model Compression across Domains—0
Margin-Based Transfer Bounds for Meta Learning with Deep Feature Embedding—0
A meta-learning approach to (re)discover plasticity rules that carve a desired function into a neural network—0
Meta-learning from Tasks with Heterogeneous Attribute SpacesCode0
Differentiable Meta-Learning of Bandit Policies—0
Meta-Information Guided Meta-Learning for Few-Shot Relation ClassificationCode0
The Advantage of Conditional Meta-Learning for Biased Regularization and Fine TuningCode0
A Closer Look at the Training Strategy for Modern Meta-LearningCode0
Show:102550
← PrevPage 271 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