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 826–850 of 3569 papers

TitleStatusHype
SAVME: Efficient Safety Validation for Autonomous Systems Using Meta-Learning—0
AutoSynth: Learning to Generate 3D Training Data for Object Point Cloud Registration—0
A Systematic Review of Few-Shot Learning in Medical Imaging—0
Graph Contrastive Learning Meets Graph Meta Learning: A Unified Method for Few-shot Node TasksCode1
Causality-Driven One-Shot Learning for Prostate Cancer Grading from MRI—0
MAD: Meta Adversarial Defense BenchmarkCode0
MVP: Meta Visual Prompt Tuning for Few-Shot Remote Sensing Image Scene Classification—0
MetaF2N: Blind Image Super-Resolution by Learning Efficient Model Adaptation from FacesCode1
Generalizable Neural Fields as Partially Observed Neural Processes—0
Convergence of Gradient-based MAML in LQR—0
BatMan-CLR: Making Few-shots Meta-Learners Resilient Against Label Noise—0
A physics-informed and attention-based graph learning approach for regional electric vehicle charging demand predictionCode2
Retrieval-Augmented Meta Learning for Low-Resource Text Classification—0
A supervised generative optimization approach for tabular data—0
Generalized Cross-domain Multi-label Few-shot Learning for Chest X-rays—0
Amortised Inference in Bayesian Neural NetworksCode0
Towards General and Efficient Online Tuning for Spark—0
Adaptive Resource Allocation for Virtualized Base Stations in O-RAN with Online Learning—0
Interactive Graph Convolutional Filtering—0
Fine-grained Recognition with Learnable Semantic Data AugmentationCode1
Self-Sampling Meta SAM: Enhancing Few-shot Medical Image Segmentation with Meta-LearningCode1
Test-Time Adaptation for Point Cloud Upsampling Using Meta-Learning—0
Meta-learning for model-reference data-driven control—0
Everything Perturbed All at Once: Enabling Differentiable Graph Attacks—0
Mixup-Augmented Meta-Learning for Sample-Efficient Fine-Tuning of Protein SimulatorsCode0
Show:102550
← PrevPage 34 of 143Next →
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