SalGAN: Visual Saliency Prediction with Generative Adversarial Networks

Understand

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.