Login (DCU Staff Only)
Login (DCU Staff Only)

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

FastSal: a computationally efficient network for visual saliency prediction

Hu, Feiyan orcid logoORCID: 0000-0001-7451-6438 and McGuinness, Kevin orcid logoORCID: 0000-0003-1336-6477 (2021) FastSal: a computationally efficient network for visual saliency prediction. In: 25th International Conference on Pattern Recognition (ICPR2020), 10-15 Jan 2021, Milan, Italy (Online).

Abstract
This paper focuses on the problem of visual saliency prediction, predicting regions of an image that tend to attract hu- man visual attention, under a constrained computational budget. We modify and test various recent efficient convolutional neural network architectures like EfficientNet and MobileNetV2 and compare them with existing state-of-the-art saliency models such as SalGAN and DeepGaze II both in terms of standard accuracy metrics like Area Under Curve (AUC) and Normalized Scanpath Saliency (NSS), and in terms of the computational complexity and model size. We find that MobileNetV2 makes an excellent backbone for a visual saliency model and can be effective even without a complex decoder. We also show that knowledge transfer from a more computationally expensive model like DeepGaze II can be achieved via pseudo-labelling an unlabelled dataset, and that this approach gives result on-par with many state-of-the-art algorithms with a fraction of the computational cost and model size.
Metadata
Item Type:Conference or Workshop Item (Paper)
Event Type:Conference
Refereed:Yes
Uncontrolled Keywords:Saliency
Subjects:Computer Science > Artificial intelligence
Computer Science > Image processing
Computer Science > Machine learning
Engineering > Signal processing
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Electronic Engineering
Research Initiatives and Centres > INSIGHT Centre for Data Analytics
Published in: 25th International Conference on Pattern Recognition, Proceedings. . Institute of Electrical and Electronics Engineers (IEEE).
Publisher:Institute of Electrical and Electronics Engineers (IEEE)
Official URL:https://www.micc.unifi.it/icpr2020/index.php/confe...
Copyright Information:© 2020 The Authors
Funders:Science Foundation Ireland (SFI) under grant number SFI/15/SIRG/3283 and SFI/12/RC/2289 P2.
ID Code:25180
Deposited On:17 Nov 2020 13:00 by Feiyan Hu . Last Modified 10 Mar 2021 14:09
Documents

Full text available as:

[thumbnail of ICPR_2020_FastSal.pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
939kB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record