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 3171–3180 of 3569 papers

TitleStatusHype
Learning Online for Unified Segmentation and Tracking Models—0
Instance-Conditional Timescales of Decay for Non-Stationary Learning—0
Learning Prototype-oriented Set Representations for Meta-Learning—0
Learning Soft Labels via Meta Learning—0
Learning State-Dependent Losses for Inverse Dynamics Learning—0
Learning Tensor Representations for Meta-Learning—0
Learning to Actively Learn: A Robust Approach—0
Learning to Adapt Multi-View Stereo by Self-Supervision—0
Learning to Adapt to Domain Shifts with Few-shot Samples in Anomalous Sound Detection—0
Learning to Adapt to Low-Resource Paraphrase Generation—0
Show:102550
← PrevPage 318 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