The strong substructure and feature attention mechanism for image semantic segmentation. (25th July 2020)

• Record Type: Journal Article
• Authors: Zhang, Yuhang; Ren, Hongshuai; Yang, Wensi; Wang, Yang; Ye, Kejiang; Xu, Cheng‐Zhong
• Is Part Of: Concurrency and computation. Volume 34:Number 12(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2020-07-25
• Subjects: semantic segmentation -- a cross‐channel structure -- satellite image recognition; Parallel processing (Electronic computers) -- Periodicals; Parallel computers -- Periodicals; 004.35
• DOI: 10.1002/cpe.5920
• Languages: English
• ISSNs: 1532-0626

Abstract

Abstract: Semantic segmentation is a hot topic in computer vision and various deep learning networks are designed to achieve higher accuracy on that by fully exploring the capability of neural networks. This paper aims to address the issue and proposes the substructures with novelty for popular networks. Meanwhile, we present a cross‐channel structure, which simultaneously reduces parameter while the kernel size becomes larger. After that, to overcome the weakness of insufficient dataset which refers to satellite image data, we propose a feature attention mechanism with generative adversarial network to enhance the images' features. We show the recognition result on the satellite image dataset with a large picture. This paper evaluates substructures on the PASCAL VOC2012 dataset and improves the mIOU from 74.68% to 88.15%.