Please use this identifier to cite or link to this item:
Title: Semantic segmentation with context encoding and multi-path decoding
Authors: Ding, Henghui
Jiang, Xudong
Shuai, Bing
Liu, Ai Qun
Wang, Gang
Keywords: Engineering::Electrical and electronic engineering
Issue Date: 2020
Source: Ding, H., Jiang, X., Shuai, B., Liu, A. Q. & Wang, G. (2020). Semantic segmentation with context encoding and multi-path decoding. IEEE Transactions On Image Processing, 29, 3520-3533.
Project: MOE2017-T3-1-001
Journal: IEEE Transactions on Image Processing
Abstract: Semantic image segmentation aims to classify every pixel of a scene image to one of many classes. It implicitly involves object recognition, localization, and boundary delineation. In this paper, we propose a segmentation network called CGBNet to enhance the paring results by context encoding and multi-path decoding. We first propose a context encoding module that generates context contrasted local feature to make use of the informative context and the discriminative local information. This context encoding module greatly improves the segmentation performance, especially for inconspicuous objects. Furthermore, we propose a scale-selection scheme to selectively fuse the parsing results from different-scales of features at every spatial position. It adaptively selects appropriate score maps from rich scales of features. To improve the parsing results of boundary, we further propose a boundary delineation module that encourages the location-specific very-low-level feature near the boundaries to take part in the final prediction and suppresses them far from the boundaries. Without bells and whistles, the proposed segmentation network achieves very competitive performance in terms of all three different evaluation metrics consistently on the four popular scene segmentation datasets, Pascal Context, SUN-RGBD, Sift Flow, and COCO Stuff, ADE20K, and Cityscapes.
ISSN: 1057-7149
DOI: 10.1109/TIP.2019.2962685
Schools: School of Electrical and Electronic Engineering 
Rights: © 2020 IEEE. All rights reserved.
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:EEE Journal Articles

Citations 5

Updated on Sep 22, 2023

Web of ScienceTM
Citations 5

Updated on Sep 18, 2023

Page view(s)

Updated on Sep 24, 2023

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.