Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

TranSalNet: Towards perceptually relevant visual saliency prediction

Lou, Jianxun, Lin, Hanhe, Marshall, David, Saupe, Dietmar and Liu, Hantao 2022. TranSalNet: Towards perceptually relevant visual saliency prediction. Neurocomputing 495 , pp. 455-467. 10.1016/j.neucom.2022.04.080

[thumbnail of 1-s2.0-S0925231222004714-main.pdf]
Preview
PDF - Published Version
Available under License Creative Commons Attribution.

Download (2MB) | Preview

Abstract

Convolutional neural networks (CNNs) have significantly advanced computational modelling for saliency prediction. However, accurately simulating the mechanisms of visual attention in the human cortex remains an academic challenge. It is critical to integrate properties of human vision into the design of CNN architectures, leading to perceptually more relevant saliency prediction. Due to the inherent inductive biases of CNN architectures, there is a lack of sufficient long-range contextual encoding capacity. This hinders CNN-based saliency models from capturing properties that emulate viewing behaviour of humans. Transformers have shown great potential in encoding long-range information by leveraging the self-attention mechanism. In this paper, we propose a novel saliency model that integrates transformer components to CNNs to capture the long-range contextual visual information. Experimental results show that the transformers provide added value to saliency prediction, enhancing its perceptual relevance in the performance. Our proposed saliency model using transformers has achieved superior results on public benchmarks and competitions for saliency prediction models.

Item Type: Article
Date Type: Publication
Status: Published
Schools: Computer Science & Informatics
Additional Information: This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/)
Publisher: Elsevier
ISSN: 0925-2312
Date of First Compliant Deposit: 26 April 2022
Date of Acceptance: 17 April 2022
Last Modified: 25 Jul 2022 09:51
URI: https://orca.cardiff.ac.uk/id/eprint/149390

Actions (repository staff only)

Edit Item Edit Item

Downloads

Downloads per month over past year

View more statistics