Search Results for author: Il-Seok Oh

Found 3 papers, 0 papers with code

Deep Anatomical Context Feature Learning for Cephalometric Landmark Detection

no code implementations IEEE Journal of Biomedical and Health Informatics 2020 Kanghan Oh, Il-Seok Oh, Van Nhat Thang Le, and Dae-Woo Lee

In this study, we present a novel framework that allows a Convolutional Neural Network (CNN) to learn richer anatomical context features during training.

Salient Explanation for Fine-grained Classification

no code implementations25 Sep 2019 Kanghan Oh, Sungchan Kim, Il-Seok Oh

Explaining the prediction of deep models has gained increasing attention to increase its applicability, even spreading it to life-affecting decisions.

Classification Object Recognition

Regional Multi-scale Approach for Visually Pleasing Explanations of Deep Neural Networks

no code implementations31 Jul 2018 Dasom Seo, Kanghan Oh, Il-Seok Oh

The experimental results demonstrate that the regional multi-scale method produces much more class-discriminative and visually pleasing saliency maps.

Feature Importance

Cannot find the paper you are looking for? You can Submit a new open access paper.