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 1261–1270 of 3569 papers

TitleStatusHype
ASAP: Learning Generalizable Online Bin Packing via Adaptive Selection After Pruning—0
Convolutional Neural Processes for Inpainting Satellite Images—0
A Sample Complexity Separation between Non-Convex and Convex Meta-Learning—0
3D Meta Point Signature: Learning to Learn 3D Point Signature for 3D Dense Shape Correspondence—0
Improved Meta Learning for Low Resource Speech Recognition—0
Improving Adversarially Robust Few-Shot Image Classification With Generalizable Representations—0
Incremental Meta-Learning via Indirect Discriminant Alignment—0
Interactive Graph Convolutional Filtering—0
Convolutional Neural Networks Can (Meta-)Learn the Same-Different Relation—0
MetaCVR: Conversion Rate Prediction via Meta Learning in Small-Scale Recommendation Scenarios—0
Show:102550
← PrevPage 127 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