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 1871–1880 of 3569 papers

TitleStatusHype
Not All Instances Contribute Equally: Instance-adaptive Class Representation Learning for Few-Shot Visual Recognition—0
Not All Negatives Are Worth Attending to: Meta-Bootstrapping Negative Sampling Framework for Link Prediction—0
Omnipush: accurate, diverse, real-world dataset of pushing dynamics with RGB-D video—0
On Finding Small Hyper-Gradients in Bilevel Optimization: Hardness Results and Improved Analysis—0
On Data Efficiency of Meta-learning—0
On-device edge learning for IoT data streams: a survey—0
One-at-a-time: A Meta-Learning Recommender-System for Recommendation-Algorithm Selection on Micro Level—0
One-Class Domain Adaptation via Meta-Learning—0
One-Class Meta-Learning: Towards Generalizable Few-Shot Open-Set Classification—0
On Enforcing Better Conditioned Meta-Learning for Rapid Few-Shot Adaptation—0
Show:102550
← PrevPage 188 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