Leveraging Conditional GANs for Uncertainty Quantification and Robust Out-of-Distribution Detection

Uncertainty quantification in deep learning is essential for providing measures of confidence in model predictions. This paper proposes a novel approach that leverages conditional Bayesian Generative Adversarial Networks (cBGANs) and Bayesian Neural Networks (BNNs) to support uncertainty-aware learn...

Descripció completa

Dades bibliogràfiques

Autors principals:	Simegnew Yihunie Alaba, Yuichi Motai, Anjon Basak, Adrienne Raglin
Format:	Artigo
Idioma:	Inglês
Publicat:	IEEE 2026-01-01
Col·lecció:	IEEE Access
Matèries:	Attention mechanism Bayesian inference conditional autoencoder generative adversarial networks uncertainty quantification conditional Bayesian GAN
Accés en línia:	https://ieeexplore.ieee.org/document/11505845/
Etiquetes:	Afegir etiqueta Sense etiquetes, Sigues el primer a etiquetar aquest registre!