MAFL: Multi-scale adversarial feature learning for saliency detection

Previous saliency detection methods usually focus on extracting features to deal with the complex background in an image. However, these methods cannot effectively capture the semantic information of images. In recent years, Generative Adversarial Network (GAN) has become a prevalent research topic. Experiments show that GAN has ability to generate high quality images that look like natural images. Inspired by the effectiveness of GAN feature learning, we propose a novel multi-scale adversarial feature learning (MAFL) model for saliency detection. In particular, we model the complete framework of saliency detection is based on two deep CNN modules: the multi-scale G-network takes natural images as inputs and generates corresponding synthetic saliency map, and we designed a novel layer in D-network, namely a correlation layer, which is used to determine whether one image is a synthetic saliency map or ground-truth saliency map. Quantitative and qualitative experiments on three benchmark datasets demonstrate that our method outperforms seven state-of-the-art methods.