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 3151–3160 of 3569 papers

Title	Date	Tasks	Status	Hype
Meta R-CNN : Towards General Solver for Instance-level Few-shot Learning	Sep 28, 2019	Few-Shot LearningFew-Shot Object Detection	—Unverified	0
Meta Learning with Differentiable Closed-form Solver for Fast Video Object Segmentation	Sep 28, 2019	FormMeta-Learning	—Unverified	0
Learning Fast Adaptation with Meta Strategy Optimization	Sep 28, 2019	Meta-Learning	CodeCode Available	0
Improving Federated Learning Personalization via Model Agnostic Meta Learning	Sep 27, 2019	Federated LearningMeta-Learning	CodeCode Available	0
Fast and Effective Adaptation of Facial Action Unit Detection Deep Model	Sep 26, 2019	Action Unit DetectionFacial Action Unit Detection	—Unverified	0
A Theoretical Analysis of the Number of Shots in Few-Shot Learning	Sep 25, 2019	ClassificationFew-Shot Learning	—Unverified	0
Learning Effective Exploration Strategies For Contextual Bandits	Sep 25, 2019	Imitation LearningLearning-To-Rank	—Unverified	0
Data Valuation using Reinforcement Learning	Sep 25, 2019	Data ValuationDomain Adaptation	CodeCode Available	0
Efficient meta reinforcement learning via meta goal generation	Sep 25, 2019	Meta-LearningMeta Reinforcement Learning	—Unverified	0
Few-Shot Regression via Learning Sparsifying Basis Functions	Sep 25, 2019	Few-Shot LearningMeta-Learning	—Unverified	0

Show:10 25 50

← PrevPage 316 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