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 41–50 of 3569 papers

Title	Date	Tasks	Status	Hype	Score
Global Convergence and Generalization Bound of Gradient-Based Meta-Learning with Deep Neural Nets	Jun 25, 2020	Few-Shot LearningMeta-Learning	CodeCode Available	2	5
Gödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement	Oct 6, 2024	Mathematical ReasoningMeta-Learning	CodeCode Available	2	5
FAMNet: Frequency-aware Matching Network for Cross-domain Few-shot Medical Image Segmentation	Dec 12, 2024	Cross-Domain Few-ShotDomain Generalization	CodeCode Available	2	5
Learning What Not to Segment: A New Perspective on Few-Shot Segmentation	Mar 15, 2022	Few-Shot Semantic SegmentationMeta-Learning	CodeCode Available	2	5
AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2	May 23, 2024	Anomaly DetectionAnomaly Segmentation	CodeCode Available	2	5
A physics-informed and attention-based graph learning approach for regional electric vehicle charging demand prediction	Sep 11, 2023	Graph LearningMeta-Learning	CodeCode Available	2	5
MetaPortrait: Identity-Preserving Talking Head Generation with Fast Personalized Adaptation	Dec 15, 2022	Face SwappingMeta-Learning	CodeCode Available	2	5
Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning	Oct 24, 2019	Meta-LearningMeta Reinforcement Learning	CodeCode Available	2	5
Neural-Fly Enables Rapid Learning for Agile Flight in Strong Winds	May 13, 2022	Meta-Learning	CodeCode Available	2	5
Attention Guided Cosine Margin For Overcoming Class-Imbalance in Few-Shot Road Object Detection	Nov 12, 2021	Few-Shot Object DetectionMeta-Learning	CodeCode Available	1	5

Show:10 25 50

← PrevPage 5 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