SOTAVerified|Agents Browse Leaderboard About Blog

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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 3251–3260 of 3569 papers

Title	Date	Tasks	Status	Hype
Learning to Segment Skin Lesions from Noisy Annotations	Jun 10, 2019	Image SegmentationMedical Image Segmentation	—Unverified	0
Domain Adaptive Dialog Generation via Meta Learning	Jun 8, 2019	Domain AdaptationMeta-Learning	CodeCode Available	0
Using learned optimizers to make models robust to input noise	Jun 8, 2019	General Classificationimage-classification	—Unverified	0
Watch, Try, Learn: Meta-Learning from Demonstrations and Reward	Jun 7, 2019	Imitation LearningMeta-Learning	—Unverified	0
One-Shot Neural Architecture Search via Compressive Sensing	Jun 7, 2019	Compressive SensingMeta-Learning	CodeCode Available	0
Adaptive Gradient-Based Meta-Learning Methods	Jun 6, 2019	Federated LearningFew-Shot Learning	CodeCode Available	0
Query-efficient Meta Attack to Deep Neural Networks	Jun 6, 2019	Adversarial AttackMeta-Learning	CodeCode Available	0
Noise Contrastive Meta-Learning for Conditional Density Estimation using Kernel Mean Embeddings	Jun 5, 2019	Density EstimationMeta-Learning	—Unverified	0
A meta-learning recommender system for hyperparameter tuning: predicting when tuning improves SVM classifiers	Jun 4, 2019	Decision MakingMeta-Learning	CodeCode Available	0
Neuromorphic Architecture Optimization for Task-Specific Dynamic Learning	Jun 4, 2019	Meta-Learning	—Unverified	0

Show:10 25 50

← PrevPage 326 of 357Next →

All datasets ML10 MT50 ML45 OMNIGLOT - 1-Shot, 20-way

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	MZ+Recon	Meta-train success rate	97.8	—	Unverified
2	MZ	Meta-train success rate	97.6	—	Unverified
3	MAML	Meta-test success rate	36	—	Unverified
4	RL^2	Meta-test success rate	10	—	Unverified
5	DnC	Meta-test success rate	5.4	—	Unverified
6	PEARL	Meta-test success rate	0	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SoftModule	Average Success Rate	60	—	Unverified
2	Multi-task multi-head SAC	Average Success Rate	35.85	—	Unverified
3	DisCor	Average Success Rate	26	—	Unverified
4	NDP	Average Success Rate	11	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MZ+Recon	Meta-test success rate (zero-shot)	18.5	—	Unverified
2	MZ	Meta-test success rate (zero-shot)	17.7	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Metadrop	% Test Accuracy	95.75	—	Unverified