%0 Journal Article
%T Regularized uncertainty-based multi-task learning model for food analysis
%A Eduardo Aguilar
%A Marc Bolaños
%A Petia Radeva
%J Journal of Visual Communication and Image Representation
%D 2019
%V 60
%F Eduardo Aguilar2019
%O MILAB; no proj
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=3298), last updated on Tue, 25 Feb 2020 14:19:49 +0100
%X 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 .
%K Multi-task models
%K Uncertainty modeling
%K Convolutional neural networks
%K Food image analysis
%K Food recognition
%K Food group recognition
%K Ingredients recognition
%K Cuisine recognition
%U https://doi.org/10.1016/j.jvcir.2019.03.011
%P 360-370