On the contextual aspects of using deep convolutional neural network for semantic image segmentation

Chunlai Wang; Lukas Mauch; Mehul Manoj Saxena; Bin Yang

doi:10.1117/1.JEI.27.5.051223

14 May 2018 On the contextual aspects of using deep convolutional neural network for semantic image segmentation

Chunlai Wang, Lukas Mauch, Mehul Manoj Saxena, Bin Yang

Author Affiliations +

Journal of Electronic Imaging, Vol. 27, Issue 5, 051223 (May 2018). https://doi.org/10.1117/1.JEI.27.5.051223

Abstract

The deep convolutional neural network (CNN) has recently shown state-of-the-art performance in many image processing tasks. We examine the use of deep CNN for semantic image segmentation, which separates an input image into multiple regions corresponding to predefined object classes. We follow the most successful deep CNN-based semantic segmentation in recent years and focus on the study of the contextual aspects. To examine the context-awareness, we manually modify the context of the input images and study the effects on the segmentation results. The experiments through systematic context changes show that the model is sensitive to some context changes. We then propose context-changing data augmentation to train context-insensitive models using images solely from the original context. We experimentally validate the effectiveness of the proposed method and summarize its limitations. Finally, we discuss the need of training context-free single-class semantic segmentation models and suggest approaches for it.

Citation Download Citation

Chunlai Wang, Lukas Mauch, Mehul Manoj Saxena, and Bin Yang "On the contextual aspects of using deep convolutional neural network for semantic image segmentation," Journal of Electronic Imaging 27(5), 051223 (14 May 2018). https://doi.org/10.1117/1.JEI.27.5.051223

Received: 13 January 2018; Accepted: 24 April 2018; Published: 14 May 2018

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