DBRS2: dense boundary regression for semantic segmentation

Jinfu Yang; Jingling Zhang; Mingai Li; Meijie Wang

doi:10.1117/1.JEI.27.5.053033

10 October 2018 DBRS²: dense boundary regression for semantic segmentation

Jinfu Yang, Jingling Zhang, Mingai Li, Meijie Wang

Author Affiliations +

Journal of Electronic Imaging, Vol. 27, Issue 5, 053033 (October 2018). https://doi.org/10.1117/1.JEI.27.5.053033

Abstract

Most of the current semantic segmentation approaches have achieved state-of-the-art performance relying on fully convolutional networks. However, the consecutive operations such as pooling or convolution striding lead to spatially disjointed object boundaries. We present a dense boundary regression architecture (DBRS²), which aims to use boundary cues to aid high-level semantic segmentation task. Specifically, we first propose a multilevel guided low-level boundary (MG-LB) learning method, where we exploit multilevel convolutional features as guidance for low-level boundary detection. The predicted MG-LB boundaries are used to enable consistent spatial grouping and enhance precise adherence to segment boundaries. Then, we present a significant global energy model based on boundary penalty and appearance penalty, which are respectively defined on the predicted boundaries and coarse segmentations obtained by the DeepLabv3 network. Finally, the refined segmentations are regressed by minimizing the global energy model. Extensive experiments over PASCAL VOC 2012, ADE20K, CamVid, and BSD500 datasets demonstrate that the proposed approach can obtain state-of-the-art performance on both semantic segmentation and boundary detection tasks.

Citation Download Citation

Jinfu Yang, Jingling Zhang, Mingai Li, and Meijie Wang "DBRS²: dense boundary regression for semantic segmentation," Journal of Electronic Imaging 27(5), 053033 (10 October 2018). https://doi.org/10.1117/1.JEI.27.5.053033

Received: 23 March 2018; Accepted: 27 August 2018; Published: 10 October 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