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 651–660 of 3569 papers

TitleStatusHype
A Simple Approach to Case-Based Reasoning in Knowledge BasesCode1
MetaFusion: Infrared and Visible Image Fusion via Meta-Feature Embedding From Object DetectionCode1
Cross-Domain Few-Shot Classification via Adversarial Task AugmentationCode1
Model-Agnostic Meta-Learning for Fast Adaptation of Deep NetworksCode1
Delving Deep Into Many-to-Many Attention for Few-Shot Video Object SegmentationCode1
Can Gradient Descent Simulate Prompting?—0
CAML: Fast Context Adaptation via Meta-Learning—0
Adaptive Variance Based Label Distribution Learning For Facial Age Estimation—0
Camera-Invariant Meta-Learning Network for Single-Camera-Training Person Re-identification—0
A Brief Summary of Interactions Between Meta-Learning and Self-Supervised Learning—0
Show:102550
← PrevPage 66 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