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 971–980 of 3569 papers

TitleStatusHype
Joint Optimization of Class-Specific Training- and Test-Time Data Augmentation in SegmentationCode0
A Meta-learning Framework for Tuning Parameters of Protection Mechanisms in Trustworthy Federated Learning—0
Learning to Learn from APIs: Black-Box Data-Free Meta-LearningCode1
Zero- and Few-Shot Event Detection via Prompt-Based Meta LearningCode1
Im-Promptu: In-Context Composition from Image PromptsCode0
HUB: Guiding Learned Optimizers with Continuous Prompt Tuning—0
Meta-prediction Model for Distillation-Aware NAS on Unseen DatasetsCode1
Test like you Train in Implicit Deep Learning—0
Meta-Learning Online Adaptation of Language ModelsCode1
Meta-learning For Vision-and-language Cross-lingual Transfer—0
Show:102550
← PrevPage 98 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