TY  - JOUR
AU  - Eduardo Aguilar
AU  - Bhalaji Nagarajan
AU  - Beatriz Remeseiro
AU  - Petia Radeva
PY  - 2022//
TI  - Bayesian deep learning for semantic segmentation of food images
T2  - CEE
JO  - Computers and Electrical Engineering
SP  - 108380
VL  - 103
PB  - Science Direct
KW  - Deep learning
KW  - Uncertainty quantification
KW  - Bayesian inference
KW  - Image segmentation
KW  - Food analysis
N2  - 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.
UR  - http://dx.doi.org/10.1016/j.compeleceng.2022.108380
N1  - MILAB
ID  - Eduardo Aguilar2022
ER  -