Convolutional Versus Operational Neural Networks for Semantic Segmentation of Maritime and Harbor Scenes

10 Pages Posted: 12 Jun 2023

See all articles by Bilge Can Pullinen

Bilge Can Pullinen

Tampere University

Mohammad Al-Sa'd

University of Helsinki

Serkan Kiranyaz

Qatar University

Moncef Gabbouj

Tampere University

Abstract

Semantic segmentation aims to associate each pixel of an image with a corresponding label that describes what is being depicted. The key aspect of semantic segmentation emanates from incorporating the classification of objects and the recognition of their shape, which is paramount for the autonomous transportation industry, e.g., maritime autonomous ships and self-driving vehicles. Various semantic segmentation solutions are based on standard Convolutional Neural Networks (CNNs). Nevertheless, recent evidence suggests that self-organized operational neural networks (Self-ONNs) can yield better performance because of their increased heterogeneity and learning capacity. This paper presents a novel network approach by combining convolutional layers with operational layers for segmenting objects in a maritime/urban environment. Overall, the findings show that the operational layers are compatible with convolutional layers for semantic segmentation tasks. While the ResNet-18 model with convolutional layers achieved 19.8%, our model SelfONN-18_2 achieved 25.4% in Mean intersection-over-union (Mean IoU) over the former validation set of ADE20K Dataset. Even with a single layer of operational layer, we achieved better results. While PSPNet-18 with convolutional layers achieved 21.3%, our model SelfONNet-18 with a single operational layer achieved 32.5% in Mean IoU over the former validation set of ADE20K Dataset.

Keywords: semantic segmentation, Operational neural networks, Self-ONNs, Generative neurons, Machine Learning, Maritime scenes

Suggested Citation

Can Pullinen, Bilge and Al-Sa'd, Mohammad and Kiranyaz, Serkan and Gabbouj, Moncef, Convolutional Versus Operational Neural Networks for Semantic Segmentation of Maritime and Harbor Scenes. Available at SSRN: https://ssrn.com/abstract=4476469 or http://dx.doi.org/10.2139/ssrn.4476469

Bilge Can Pullinen (Contact Author)

Tampere University ( email )

Tampere, FIN-33101
Finland

Mohammad Al-Sa'd

University of Helsinki ( email )

University of Helsinki
Helsinki, FIN-00014
Finland

Serkan Kiranyaz

Qatar University ( email )

College of Law
Qatar University
Doha, 2713
Qatar

Moncef Gabbouj

Tampere University ( email )

Tampere, FIN-33101
Finland

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
41
Abstract Views
369
PlumX Metrics