SalGAN: Visual Saliency Prediction with Generative Adversarial Networks

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 versi...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Pan, Junting, Cristian Canton Ferrer, McGuinness, Kevin, O'Connor, Noel E, Torres, Jordi, Sayrol, Elisa, Giro-i-Nieto, Xavier
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 01.07.2018
Subjects
Artificial neural networks
Back propagation networks
Generative adversarial networks
Ground truth
Mathematical models
Neural networks
Salience
Source code
Online AccessGet full text

Cover

More Information
Summary: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/.
ISSN:2331-8422