← Search

Keunseo Kim

2 accepted papers

2023

Inverse-Reference Priors for Fisher Regularization of Bayesian Neural Networks

AAAI 2023technical

Recent studies have shown that the generalization ability of deep neural networks (DNNs) is closely related to the Fisher information matrix (FIM) calculated during the early training phase. Several methods have been proposed to regularize the FIM for increased generalization of DNNs. However, they…

Cited by 3SourcePDFScholar
2021

Locally Most Powerful Bayesian Test for Out-of-Distribution Detection using Deep Generative Models

NeurIPS 2021poster

Several out-of-distribution (OOD) detection scores have been recently proposed for deep generative models because the direct use of the likelihood threshold for OOD detection has been shown to be problematic. In this paper, we propose a new OOD score based on a Bayesian hypothesis test called the lo…

Cited by 19SourcePDFScholar