Saliency detection by conditional generative adversarial network

Xiaoxu Cai; Hui Yu

doi:10.1117/12.2306421

10 April 2018 Saliency detection by conditional generative adversarial network

Xiaoxu Cai, Hui Yu

Proceedings Volume 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017); 1061541 (2018) https://doi.org/10.1117/12.2306421
Event: Ninth International Conference on Graphic and Image Processing, 2017, Qingdao, China

Abstract

Detecting salient objects in images has been a fundamental problem in computer vision. In recent years, deep learning has shown its impressive performance in dealing with many kinds of vision tasks. In this paper, we propose a new method to detect salient objects by using Conditional Generative Adversarial Network (GAN). This type of network not only learns the mapping from RGB images to salient regions, but also learns a loss function for training the mapping. To the best of our knowledge, this is the first time that Conditional GAN has been used in salient object detection. We evaluate our saliency detection method on 2 large publicly available datasets with pixel accurate annotations. The experimental results have shown the significant and consistent improvements over the state-of-the-art method on a challenging dataset, and the testing speed is much faster.

Citation Download Citation

Xiaoxu Cai and Hui Yu "Saliency detection by conditional generative adversarial network", Proc. SPIE 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017), 1061541 (10 April 2018); https://doi.org/10.1117/12.2306421

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available