BASNet: improving semantic segmentation via boundary-assistant symmetrical network

Yong Qiang; Quan Zhou; Huiming Shi; Xin Jin; Weihua Ou; Longin Jan Latecki

doi:10.1117/12.2601128

28 October 2021 BASNet: improving semantic segmentation via boundary-assistant symmetrical network

Yong Qiang, Quan Zhou, Huiming Shi, Xin Jin, Weihua Ou, Longin Jan Latecki

Proceedings Volume 11884, International Symposium on Artificial Intelligence and Robotics 2021; 1188404 (2021) https://doi.org/10.1117/12.2601128
Event: International Symposium on Artificial Intelligence and Robotics 2021, 2021, Fukuoka, Japan

Abstract

Recently, boundary information has gained more attention in improving the performance of semantic segmentation. This paper presents a novel symmetrical network, called BASNet, which contains four components: the pre-trained ResNet-101 backbone, semantic segmentation branch (SSB), boundary detection branch (BDB), and aggregation module (AM). More specifically, our BDB only focuses on processing boundary-related information using a series of spatial attention blocks (SABs). On the other hand, a set of global attention blocks (GABs) are used in SSB to further capture more accurate object boundary information and semantic information. Finally, the outputs of SSB and BDB are fed into AM, which merges the features from SSB and BDB to boost performance. The exhaustive experimental results show that our method not only predicts the boundaries of objects more accurately, but also improves the performance of semantic segmentation.

Citation Download Citation

Yong Qiang, Quan Zhou, Huiming Shi, Xin Jin, Weihua Ou, and Longin Jan Latecki "BASNet: improving semantic segmentation via boundary-assistant symmetrical network", Proc. SPIE 11884, International Symposium on Artificial Intelligence and Robotics 2021, 1188404 (28 October 2021); https://doi.org/10.1117/12.2601128

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