Papers

Basic information

Name ENDO KAZUKI
Belonging department Management Information Course,Department of Business,Faculty of Humanities and Social Sciences
Occupation name Associate Professor
researchmap researcher code
researchmap agency

Title

ILIAC: Efficient classification of degraded images using knowledge distillation with cutout data augmentation

Bibliography怀Type

Joint Author

Summary

We numerically showed the effectiveness of the cutout data augmentation under the knowledge distillation to train the classifier of degraded images.  
Dinesh Daultani, Masayuki Tanaka, Masatoshi Okutomi, Kazuki Endo

Magazine(name)

Proceedings of IS&T Electronic Imaging 2023

Date of Issue

202301