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

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

SalGAN: visual saliency prediction with generative adversarial networks

Pan, Junting, Sayrol, Elisa, Giró-i-Nieto, Xavier orcid logoORCID: 0000-0002-9935-5332, Canton Ferrer, Cristian, Torres, Jordi, McGuinness, Kevin orcid logoORCID: 0000-0003-1336-6477 and O'Connor, Noel E. orcid logoORCID: 0000-0002-4033-9135 (2017) SalGAN: visual saliency prediction with generative adversarial networks. In: CVPR SUNw: Scene Understanding Workshop 2017, July 26, 2017, Hawaii.

Abstract
We introduce SalGAN, a deep convolutional neural network for visual saliency prediction trained with adversarial examples. The first stage of the network consists of a generator model whose weights are learned by back-propagation computed from a binary cross entropy (BCE) loss over downsampled versions of the saliency maps. The resulting prediction is processed by a discriminator network trained to solve a binary classification task between the saliency maps generated by the generative stage and the ground truth ones. Our experiments show how adversarial training allows reaching state-of-the-art performance across different metrics when combined with a widely-used loss function like BCE. Our results can be reproduced with the source code and trained models available at https://imatge-upc.github. io/saliency-salgan-2017/.
Metadata
Item Type:Conference or Workshop Item (Paper)
Event Type:Workshop
Refereed:Yes
Subjects:Computer Science > Machine learning
Computer Science > Artificial intelligence
Computer Science > Image processing
DCU Faculties and Centres:Research Initiatives and Centres > INSIGHT Centre for Data Analytics
DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Publisher:IEEE
Official URL:https://imatge-upc.github.io/saliency-salgan-2017/
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:Science Foundation Ireland 15/SIRG/3283, Spanish Ministry of Science and Innovation TIN2015-65316, SGR-1051
ID Code:21834
Deposited On:03 Jul 2017 09:57 by Kevin Mcguinness . Last Modified 25 Jan 2019 09:44
Documents

Full text available as:

[thumbnail of Extended pre-print]
Preview
PDF (Extended pre-print) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
1MB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record