PT Journal
AU Eduardo Aguilar
   Bhalaji Nagarajan
   Beatriz Remeseiro
   Petia Radeva
TI Bayesian deep learning for semantic segmentation of food images
SO Computers and Electrical Engineering
JI CEE
PY 2022
BP 108380
VL 103
DI 10.1016/j.compeleceng.2022.108380
DE Deep learning; Uncertainty quantification; Bayesian inference; Image segmentation; Food analysis
AB Deep learning has provided promising results in various applications; however, algorithms tend to be overconfident in their predictions, even though they may be entirely wrong. Particularly for critical applications, the model should provide answers only when it is very sure of them. This article presents a Bayesian version of two different state-of-the-art semantic segmentation methods to perform multi-class segmentation of foods and estimate the uncertainty about the given predictions. The proposed methods were evaluated on three public pixel-annotated food datasets. As a result, we can conclude that Bayesian methods improve the performance achieved by the baseline architectures and, in addition, provide information to improve decision-making. Furthermore, based on the extracted uncertainty map, we proposed three measures to rank the images according to the degree of noisy annotations they contained. Note that the top 135 images ranked by one of these measures include more than half of the worst-labeled food images.
ER