A Multi-Task Bayesian Deep Neural Net for Detecting Life-Threatening Infant Incidents From Head Images

Loading...
Thumbnail Image

Access rights

openAccess
acceptedVersion

URL

Journal Title

Journal ISSN

Volume Title

A4 Artikkeli konferenssijulkaisussa

Date

Major/Subject

Mcode

Degree programme

Language

en

Pages

5

Series

2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings, pp. 3006-3010

Abstract

The notorious incident of sudden infant death syndrome (SIDS) can easily happen to a newborn due to many environmental factors. To prevent such tragic incidents from happening, we propose a multi-task deep learning framework that detects different facial traits and two life-threatening indicators, i.e. which facial parts are occluded or covered, by analyzing the infant head image. Furthermore, we extend and adapt the recently developed models that capture data-dependent uncertainty from noisy observations for our application. The experimental results show significant improvements on YunInfants dataset across most of the tasks over the models that simply adopt the regular cross-entropy losses without addressing the effect of the underlying uncertainties.

Description

Keywords

Other note

Citation

Wang, T-J J, Laaksonen, J, Liao, Y-P, Wu, B-Z & Shen, S-Y 2019, A Multi-Task Bayesian Deep Neural Net for Detecting Life-Threatening Infant Incidents From Head Images. in 2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings., 8803332, IEEE, pp. 3006-3010, IEEE International Conference on Image Processing, Taipei, Taiwan, Republic of China, 22/09/2019. https://doi.org/10.1109/ICIP.2019.8803332