SOTAVerified

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 AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 2101–2150 of 3569 papers

TitleStatusHype
Fast Training of Neural Lumigraph Representations using Meta Learning—0
Generalized Zero-Shot Learning using Multimodal Variational Auto-Encoder with Semantic Concepts—0
Semi-supervised Meta-learning with Disentanglement for Domain-generalised Medical Image SegmentationCode1
Fairness in Cardiac MR Image Analysis: An Investigation of Bias Due to Data Imbalance in Deep Learning Based Segmentation—0
Mutual-Information Based Few-Shot ClassificationCode1
Long-term Cross Adversarial Training: A Robust Meta-learning Method for Few-shot Classification TasksCode0
Multimodal Emergent Fake News Detection via Meta Neural Process Networks—0
MetaAvatar: Learning Animatable Clothed Human Models from Few Depth ImagesCode1
BiAdam: Fast Adaptive Bilevel Optimization Methods—0
Compositional federated learning: Applications in distributionally robust averaging and meta learning—0
Transfer Bayesian Meta-learning via Weighted Free Energy MinimizationCode1
Multi-Pair Text Style Transfer on Unbalanced Data—0
Task Attended Meta-Learning for Few-Shot Learning—0
Delving Deep Into Many-to-Many Attention for Few-Shot Video Object SegmentationCode1
Transformation Invariant Few-Shot Object Detection—0
Person30K: A Dual-Meta Generalization Network for Person Re-Identification—0
EvoGrad: Efficient Gradient-Based Meta-Learning and Hyperparameter OptimizationCode1
Attacking Few-Shot Classifiers with Adversarial Support Poisoning—0
On Contrastive Representations of Stochastic ProcessesCode1
Meta-Calibration: Learning of Model Calibration Using Differentiable Expected Calibration ErrorCode1
How Low Can We Go: Trading Memory for Error in Low-Precision TrainingCode0
MetaBalance: High-Performance Neural Networks for Class-Imbalanced Data—0
Transductive Few-Shot Learning: Clustering is All You Need?Code1
HELP: Hardware-Adaptive Efficient Latency Prediction for NAS via Meta-LearningCode1
SPeCiaL: Self-Supervised Pretraining for Continual Learning—0
Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective AdaptationCode1
Generative Conversational Networks—0
Contextualizing Meta-Learning via Learning to DecomposeCode0
Dynamic Distillation Network for Cross-Domain Few-Shot Recognition with Unlabeled DataCode1
Learning Deep Morphological Networks with Neural Architecture SearchCode0
Automated Machine Learning Techniques for Data StreamsCode1
Domain Generalization on Medical Imaging Classification using Episodic Training with Task Augmentation—0
Robust Graph Meta-learning for Weakly-supervised Few-shot Node Classification—0
Knowledge Consolidation based Class Incremental Online Learning with Limited Data—0
Meta-Learning for Symbolic Hyperparameter DefaultsCode0
Attentional Meta-learners for Few-shot Polythetic ClassificationCode0
Probabilistic task modelling for meta-learningCode0
Memory-Based Optimization Methods for Model-Agnostic Meta-Learning and Personalized Federated LearningCode0
Learning Functional Priors and Posteriors from Data and Physics—0
Provably Faster Algorithms for Bilevel OptimizationCode1
Meta-Learning to Compositionally GeneralizeCode1
Reinforced Few-Shot Acquisition Function Learning for Bayesian Optimization—0
BERT Learns to Teach: Knowledge Distillation with Meta LearningCode1
RegMix: Data Mixing Augmentation for Regression—0
Evaluating Meta-Feature Selection for the Algorithm Recommendation ProblemCode0
Self-Supervision & Meta-Learning for One-Shot Unsupervised Cross-Domain DetectionCode1
A Meta Learning Approach to Discerning Causal Graph Structure—0
Meta-learning with implicit gradients in a few-shot setting for medical image segmentation—0
Meta-learning for downstream aware and agnostic pretraining—0
Meta-Learning Reliable Priors in the Function Space—0
Show:102550
← PrevPage 43 of 72Next →
All datasetsML10MT50ML45OMNIGLOT - 1-Shot, 20-way

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MZ+ReconMeta-train success rate97.8—Unverified
2MZMeta-train success rate97.6—Unverified
3MAMLMeta-test success rate36—Unverified
4RL^2Meta-test success rate10—Unverified
5DnCMeta-test success rate5.4—Unverified
6PEARLMeta-test success rate0—Unverified
#ModelMetricClaimedVerifiedStatus
1SoftModuleAverage Success Rate60—Unverified
2Multi-task multi-head SACAverage Success Rate35.85—Unverified
3DisCorAverage Success Rate26—Unverified
4NDPAverage Success Rate11—Unverified
#ModelMetricClaimedVerifiedStatus
1MZ+ReconMeta-test success rate (zero-shot)18.5—Unverified
2MZMeta-test success rate (zero-shot)17.7—Unverified
#ModelMetricClaimedVerifiedStatus
1Metadrop% Test Accuracy95.75—Unverified