TY  - JOUR
AU  - Eduardo Aguilar
AU  - Marc Bolaños
AU  - Petia Radeva
PY  - 2019//
TI  - Regularized uncertainty-based multi-task learning model for food analysis
T2  - JVCIR
JO  - Journal of Visual Communication and Image Representation
SP  - 360
EP  - 370
VL  - 60
KW  - Multi-task models
KW  - Uncertainty modeling
KW  - Convolutional neural networks
KW  - Food image analysis
KW  - Food recognition
KW  - Food group recognition
KW  - Ingredients recognition
KW  - Cuisine recognition
N2  - Food plays an important role in several aspects of our daily life. Several computer vision approaches have been proposed for tackling food analysis problems, but very little effort has been done in developing methodologies that could take profit of the existent correlation between tasks. In this paper, we propose a new multi-task model that is able to simultaneously predict different food-related tasks, e.g. dish, cuisine and food categories. Here, we extend the homoscedastic uncertainty modeling to allow single-label and multi-label classification and propose a regularization term, which jointly weighs the tasks as well as their correlations. Furthermore, we propose a new Multi-Attribute Food dataset and a new metric, Multi-Task Accuracy. We prove that using both our uncertainty-based loss and the class regularization term, we are able to improve the coherence of outputs between different tasks. Moreover, we outperform the use of task-specific models on classical measures like accuracy or .
UR  - https://doi.org/10.1016/j.jvcir.2019.03.011
N1  - MILAB; no proj
ID  - Eduardo Aguilar2019
ER  -