# SalGAN: Visual Saliency Prediction with Generative Adversarial Networks

4 Jan 2017Junting PanCristian Canton FerrerKevin McGuinnessNoel E. O'ConnorJordi TorresElisa SayrolXavier Giro-i-Nieto

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... (read more)

PDF Abstract