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 2971–2980 of 3569 papers

TitleStatusHype
Challenge Closed-book Science Exam: A Meta-learning Based Question Answering System—0
Automatic low-bit hybrid quantization of neural networks through meta learning—0
ST^2: Small-data Text Style Transfer via Multi-task Meta-Learning—0
Learning to Classify Intents and Slot Labels Given a Handful of Examples—0
Dynamic Knowledge Graph-based Dialogue Generation with Improved Adversarial Meta-Learning—0
Knowledge-graph based Proactive Dialogue Generation with Improved Meta-Learning—0
A Comprehensive Overview and Survey of Recent Advances in Meta-Learning—0
Meta-Meta Classification for One-Shot LearningCode0
Divergent Search for Few-Shot Image Classification—0
Self-Supervised Tuning for Few-Shot Segmentation—0
Show:102550
← PrevPage 298 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