Supervised adversarial networks for image saliency detection

Hengyue Pan; Xin Niu; Rongchun Li; Siqi Shen; Yong Dou

doi:10.1117/12.2557190

Translator Disclaimer

3 January 2020 Supervised adversarial networks for image saliency detection

Hengyue Pan, Xin Niu, Rongchun Li, Siqi Shen, Yong Dou

Author Affiliations +

Proceedings Volume 11373, Eleventh International Conference on Graphics and Image Processing (ICGIP 2019); 113730H (2020) https://doi.org/10.1117/12.2557190
Event: Eleventh International Conference on Graphics and Image Processing, 2019, Hangzhou, China

Abstract

In the past few years, Generative Adversarial Network (GAN) became a prevalent research topic. GAN has ability to generate good quality images that look like natural images from a random vector. 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). 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. Experimental results on Pascal VOC 2012 database show that the SAN model can generate high quality saliency maps for many complicate natural images.

Citation Download Citation

Hengyue Pan, Xin Niu, Rongchun Li, Siqi Shen, and Yong Dou "Supervised adversarial networks for image saliency detection", Proc. SPIE 11373, Eleventh International Conference on Graphics and Image Processing (ICGIP 2019), 113730H (3 January 2020); https://doi.org/10.1117/12.2557190

ACCESS THE FULL ARTICLE