Browse DORAS
Browse Theses
Latest Additions
Creative Commons License
Except where otherwise noted, content on this site is licensed for use under a:

SalGAN: visual saliency prediction with generative adversarial networks

Pan, Junting and Sayrol, Elisa and Giro-i-Nieto, Xavier and Canton Ferrer, Cristian and Torres, Jordi and McGuinness, Kevin and O'Connor, Noel E. (2017) SalGAN: visual saliency prediction with generative adversarial networks. In: CVPR SUNw: Scene Understanding Workshop 2017, July 26, 2017, Hawaii.

Full text available as:

PDF (Extended pre-print) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader


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/.

Item Type:Conference or Workshop Item (Paper)
Event Type:Workshop
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
Official URL:
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 10:57 by Kevin McGuinness. Last Modified 21 Sep 2017 09:27

Download statistics

Archive Staff Only: edit this record