Supervised Adversarial Networks for Image Saliency Detection

TL;DR

This paper introduces Supervised Adversarial Networks (SAN), a novel model for image saliency detection that leverages supervised learning and adversarial training to generate high-quality saliency maps, outperforming previous methods.

Contribution

The paper proposes SAN, a supervised adversarial framework with a conv-comparison layer for improved saliency detection, combining GAN principles with class label supervision.

Findings

SAN produces high-quality saliency maps on Pascal VOC 2012.

The conv-comparison layer enhances the similarity between synthetic and ground-truth saliency maps.

Experimental results demonstrate SAN's superiority over existing saliency detection methods.

Abstract

In the past few years, Generative Adversarial Network (GAN) became a prevalent research topic. By defining two convolutional neural networks (G-Network and D-Network) and introducing an adversarial procedure between them during the training process, GAN has ability to generate good quality images that look like natural images from a random vector. Besides image generation, GAN may have potential to deal with wide range of real world problems. In this paper, we follow the basic idea of GAN and propose a novel model for image saliency detection, which is called Supervised Adversarial Networks (SAN). Specifically, SAN also trains two models simultaneously: the G-Network takes natural images as inputs and generates corresponding saliency maps (synthetic saliency maps), and the D-Network is trained to determine whether one sample is a synthetic saliency map or ground-truth saliency map. However, different from GAN, the proposed method uses fully supervised learning to learn both G-Network and D-Network by applying class labels of the training set. Moreover, a novel kind of layer call conv-comparison layer is introduced into the D-Network to further improve the saliency performance by forcing the high-level feature of synthetic saliency maps and ground-truthes as similar as possible. Experimental results on Pascal VOC 2012 database show that the SAN model can generate high quality saliency maps for many complicate natural images.