Deep learning vs. traditional algorithms for saliency prediction of distorted images

Zhao, Xin, Lin, Hanhe, Guo, Pengfei, Saupe, Dietmar and Liu, Hantao ORCID: https://orcid.org/0000-0003-4544-3481 2020. Deep learning vs. traditional algorithms for saliency prediction of distorted images. Presented at: 27th IEEE International Conference on Image Processing (ICIP 2020), United Arab Emirates, 25-28 October 2020.

Preview

PDF - Accepted Post-Print Version Download (4MB) | Preview

Abstract

Saliency has been widely studied in relation to image quality assessment (IQA). The optimal use of saliency in IQA metrics, however, is nontrivial and largely depends on whether saliency can be accurately predicted for images containing various distortions. Although tremendous progress has been made in saliency modelling, very little is known about whether and to what extent state-of-the-art methods are beneficial for saliency prediction of distorted images. In this paper, we analyse the ability of deep learning versus traditional algorithms in predicting saliency, based on an IQA-aware saliency benchmark, the SIQ288 database. Building off the variations in model performance, we make recommendations for model selections for IQA applications.

Item Type:	Conference or Workshop Item (Paper)
Status:	In Press
Schools:	Computer Science & Informatics
Date of First Compliant Deposit:	3 June 2020
Date of Acceptance:	16 May 2020
Last Modified:	07 Nov 2022 10:24
URI:	https://orca.cardiff.ac.uk/id/eprint/132140

Citation Data

Cited 1 time in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item