Transfer learning focuses on building better predictive models by exploiting knowledge
gained in previous related tasks, being able to soften the traditional supervised learning …

Modeling the preferences of agents over a set of alternatives is a principal concern in many
areas. The dominant approach has been to find a single reward/utility function with the …

Traditionally, convolutional neural networks are trained for semantic segmentation by having
an image given as input and the segmented mask as output. In this work, we propose a …

Local Binary Pattern (LBP) is a traditional descriptor for texture analysis that gained attention
in the last decade. Being robust to several properties such as invariance to illumination …

Breast cancer is a highly mutable and rapidly evolving disease, with a large worldwide
incidence. Even though, it is estimated that approximately 90% of the cases are treatable …

Digital colposcopy is a low-cost technology widely used in the early detection of cervical
cancer and in the forensic evaluation of sexual assault. It consists on the observation of the …