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 1741–1750 of 3569 papers

TitleStatusHype
Learning To Learn and Remember Super Long Multi-Domain Task SequenceCode1
Meta Distribution Alignment for Generalizable Person Re-IdentificationCode0
Towards Multi-Domain Single Image Dehazing via Test-Time Training—0
MetaFSCIL: A Meta-Learning Approach for Few-Shot Class Incremental Learning—0
Improving Adversarially Robust Few-Shot Image Classification With Generalizable Representations—0
Distributed Evolution Strategies Using TPUs for Meta-Learning—0
Relational Experience Replay: Continual Learning by Adaptively Tuning Task-wise Relationship—0
Delving into Sample Loss Curve to Embrace Noisy and Imbalanced DataCode0
Feature-context driven Federated Meta-Learning for Rare Disease Prediction—0
Recursive Least-Squares Estimator-Aided Online Learning for Visual TrackingCode1
Show:102550
← PrevPage 175 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