Empirical study of the modulus as activation function in computer vision applications

In this work we propose a new non-monotonic activation function: the modulus. The majority of the reported research on nonlinearities is focused on monotonic functions. We empirically demonstrate how by using the modulus activation function on computer vision tasks the models generalize better than...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Vallés-Pérez, Iván, Soria-Olivas, Emilio, Martínez-Sober, Marcelino, Serrano-López, Antonio J, Vila-Francés, Joan, Gómez-Sanchís, Juan
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 15.01.2023
Subjects
Computer vision
Derivatives
Nonlinearity
Online AccessGet full text

Cover

More Information
Summary:In this work we propose a new non-monotonic activation function: the modulus. The majority of the reported research on nonlinearities is focused on monotonic functions. We empirically demonstrate how by using the modulus activation function on computer vision tasks the models generalize better than with other nonlinearities - up to a 15% accuracy increase in CIFAR100 and 4% in CIFAR10, relative to the best of the benchmark activations tested. With the proposed activation function the vanishing gradient and dying neurons problems disappear, because the derivative of the activation function is always 1 or -1. The simplicity of the proposed function and its derivative make this solution specially suitable for TinyML and hardware applications.
ISSN:2331-8422