Tag: self-supervised learning

Researchers have developed BHyGNN+, a self-supervised framework that learns representations of heterophilic hypergraphs without labels by contrasting each hypergraph against ...

Researchers have unveiled xvr, a self-supervised AI framework that adapts a pretrained neural network to any patient's anatomy in about ...

A large-scale study finds that pretraining tabular self-supervised models on carefully selected subsets of 100 to 1000 unlabeled examples often ...

A new dual-masked graph autoencoder called DM-GAE maps mineral prospectivity in Tibet with high accuracy despite scarce labeled deposits, outperforming ...

A new scoping review of 39 studies maps a decade of progress in using speech and voice as AI-driven biomarkers ...

A self-supervised Vision Transformer framework that fuses multi-scale geological maps with aeromagnetic data has substantially outperformed conventional methods in mapping ...

Researchers have developed GRAB-FL, a graph-aware federated learning framework that uses graph neural networks to assign trust scores to client ...

Researchers have developed SA-IDS, a self-supervised intrusion detection system that learns normal behavior without labeled data and adapts to drift ...

Researchers have developed CROWN, a self-supervised visual foundation model pretrained on more than ten million cytology images that achieved top ...

A new self-supervised domain adaptation framework uses monocular depth foundation models and consistency-aware learning to make stereo matching networks reliable ...