Histogram-based Deep Neural Network for Quantification
Pablo González, Juan José dal Coz
Artificial Intelligence Center, University of Oviedo, 33204 Gijón, Spain


                                          Abstract
                                          In recent times, deep neural networks (DNN) have been successfully applied to multiple machine learning problems. In the
                                          quantification field, there have been a couple of attempts that envision the ability of these networks to tackle this problem
                                          specifically. This paper proposes a DNN architecture called HistNet, that is based on histogram representations and is able to
                                          handle binary and multiclass quantification problems without the need of an underlying classifier. Our method achieves
                                          state-of-the-art results in two public datasets, one from the field of computer vision (Fashion-MNIST) and the other dealing
                                          with a natural language processing problem (IMDB).




LQ 2021: 1st International Workshop on Learning to Quantify, Gold
Coast, AU, November 1 and November 5, 2021.
$ gonzalezgpablo@uniovi.es (P. González); juanjo@uniovi.es
(J. J. d. Coz)
                                    © 2021 Copyright for this paper by its authors. Use permitted under Creative
                                    Commons License Attribution 4.0 International (CC BY 4.0).
 CEUR
 Workshop
 Proceedings
               http://ceur-ws.org
               ISSN 1613-0073       CEUR Workshop Proceedings (CEUR-WS.org)