Towards a framework for the democratisation of deep semantic segmentation models

Abstract

[Abstract] Semantic segmentation models based on deep learning techniques have been successfully applied in several contexts. However, non-expert users might find challenging the use of those techniques due to several reasons, including the necessity of trying different algorithms implemented in heterogeneous libraries, the configuration of hyperparameters, the lack of support of many state-of-the-art algorithms for training them on custom datasets, or the variety of metrics employed to evaluate semantic segmentation models. In this work, we present the first steps towards the development of a framework that facilitates the construction and usage of deep segmentation models.