In the past few years, Generative Adversarial Network (GAN) became a prevalent research topic. GAN has ability togenerate good quality images that look like natural images from a random vector. In this paper, we follow the basic ideaof GAN and propose a novel model for image saliency detection, which is called Supervised Adversarial Networks(SAN). However, different from GAN, the proposed method uses fully supervised learning to learn both G-Network andD-Network by applying class labels of the training set. Moreover, a novel kind of layer call conv-comparison layer isintroduced into the D-Network to further improve the saliency performance. Experimental results on Pascal VOC 2012database show that the SAN model can generate high quality saliency maps for many complicate natural images.
展开▼