SalGAN: Visual Saliency Prediction with Generative Adversarial Networks
Junting Pan, Cristian Canton Ferrer, Kevin McGuinness, Noel E. O'Connor, Jordi Torres, Elisa Sayrol, Xavier Giro-i-Nieto
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/imatge-upc/salganOfficialpytorch★ 0
- github.com/imatge-upc/saliency-salgan-2017pytorch★ 0
- github.com/wangxiao5791509/cmSalGAN_PyTorchpytorch★ 0
- github.com/imatge-upc/saliency-2019-SalBCEpytorch★ 0
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/.