A novel fully convolutional network for visual saliency prediction

Ghariba, Bashir Muftah and Shehata, Mohamed S. and McGuire, Peter (2020) A novel fully convolutional network for visual saliency prediction. PeerJ Computer Science, 6. ISSN 2376-5992

[img] [English] PDF - Published Version
Available under License Creative Commons Attribution Non-commercial.

Download (4MB)

Abstract

A human Visual System (HVS) has the ability to pay visual attention, which is one of the many functions of the HVS. Despite the many advancements being made in visual saliency prediction, there continues to be room for improvement. Deep learning has recently been used to deal with this task. This study proposes a novel deep learning model based on a Fully Convolutional Network (FCN) architecture. The proposed model is trained in an end-to-end style and designed to predict visual saliency. The entire proposed model is fully training style from scratch to extract distinguishing features. The proposed model is evaluated using several benchmark datasets, such as MIT300, MIT1003, TORONTO, and DUT-OMRON. The quantitative and qualitative experiment analyses demonstrate that the proposed model achieves superior performance for predicting visual saliency.

Item Type: Article
URI: http://research.library.mun.ca/id/eprint/14885
Item ID: 14885
Additional Information: Memorial University Open Access Author's Fund
Keywords: Deep learning, Convolutional neural networks, Fully Convolutional Network, Semantic Segmentation, Encoder-decoder architecture, Human eye fixation
Department(s): Engineering and Applied Science, Faculty of
Date: 13 July 2020
Date Type: Publication
Digital Object Identifier (DOI): https://doi.org/10.7717/peerj-cs.280
Related URLs:

Actions (login required)

View Item View Item

Downloads

Downloads per month over the past year

View more statistics