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 3091–3100 of 3569 papers

Title	Date	Tasks	Status	Hype
Reproducing Meta-learning with differentiable closed-form solvers	Mar 6, 2019	FormMeta-Learning	CodeCode Available	0
Repurposing Pretrained Models for Robust Out-of-domain Few-Shot Learning	Mar 16, 2021	Few-Shot LearningMeta-Learning	CodeCode Available	0
Top-Related Meta-Learning Method for Few-Shot Object Detection	Jul 14, 2020	Few-Shot Object DetectionMeta-Learning	CodeCode Available	0
Style Variable and Irrelevant Learning for Generalizable Person Re-identification	Sep 12, 2022	DiversityDomain Generalization	CodeCode Available	0
Zero-shot task adaptation by homoiconic meta-mapping	May 23, 2019	Meta-Learning	CodeCode Available	0
Incremental Few-Shot Learning with Attention Attractor Networks	Oct 16, 2018	Few-Shot LearningGeneral Classification	CodeCode Available	0
Multi-Modal Fusion by Meta-Initialization	Oct 10, 2022	Few-Shot Learningimage-classification	CodeCode Available	0
Incorporating Test-Time Optimization into Training with Dual Networks for Human Mesh Recovery	Jan 25, 2024	Human Mesh RecoveryMeta-Learning	CodeCode Available	0
In-Context Learning through the Bayesian Prism	Jun 8, 2023	Bayesian InferenceIn-Context Learning	CodeCode Available	0
In-Context Learning for MIMO Equalization Using Transformer-Based Sequence Models	Nov 10, 2023	In-Context LearningMeta-Learning	CodeCode Available	0

Show:10 25 50

← PrevPage 310 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