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 211–220 of 3569 papers

TitleStatusHype
Can Learned Optimization Make Reinforcement Learning Less Difficult?Code1
Few-shot Relation Extraction via Bayesian Meta-learning on Relation GraphsCode1
CD-FSOD: A Benchmark for Cross-domain Few-shot Object DetectionCode1
Few-Shot Scene Adaptive Crowd Counting Using Meta-LearningCode1
Adaptive Multi-Teacher Knowledge Distillation with Meta-LearningCode1
Few-Shot Unsupervised Continual Learning through Meta-ExamplesCode1
Distilling Meta Knowledge on Heterogeneous Graph for Illicit Drug Trafficker Detection on Social MediaCode1
Fine-grained Recognition with Learnable Semantic Data AugmentationCode1
Flexible Dataset Distillation: Learn Labels Instead of ImagesCode1
Adversarial Feature Augmentation for Cross-domain Few-shot ClassificationCode1
Show:102550
← PrevPage 22 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