SOTAVerified|Agents Browse Leaderboard About

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 881–890 of 3569 papers

Title	Date	Tasks	Status	Hype	Score
Effective Few-Shot Named Entity Linking by Meta-Learning	Jul 12, 2022	Entity LinkingKnowledge Base Completion	CodeCode Available	0	5
Bayesian Meta Sampling for Fast Uncertainty Adaptation	May 1, 2020	Meta-Learning	CodeCode Available	0	5
Learning to adapt: a meta-learning approach for speaker adaptation	Aug 30, 2018	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	CodeCode Available	0	5
Learning One-Shot Imitation from Humans without Humans	Nov 4, 2019	Imitation LearningMeta-Learning	CodeCode Available	0	5
Deep Task-Based Analog-to-Digital Conversion	Jan 29, 2022	Meta-LearningQuantization	CodeCode Available	0	5
Meta-learning algorithms for Few-Shot Computer Vision	Sep 30, 2019	Few-Shot Image ClassificationFew-Shot Learning	CodeCode Available	0	5
Adaptive Fine-Grained Sketch-Based Image Retrieval	Jul 4, 2022	Image RetrievalMeta-Learning	CodeCode Available	0	5
Learning New Tasks from a Few Examples with Soft-Label Prototypes	Oct 31, 2022	Few-Shot LearningMeta-Learning	CodeCode Available	0	5
Algorithm Selection on a Meta Level	Jul 20, 2021	Ensemble LearningMeta-Learning	CodeCode Available	0	5
Learning How to Demodulate from Few Pilots via Meta-Learning	Mar 6, 2019	Meta-Learning	CodeCode Available	0	5

Show:10 25 50

← PrevPage 89 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