Please use this identifier to cite or link to this item:
Title: Semantic correlation promoted shape-variant context for segmentation
Authors: Ding, Henghui
Jiang, Xudong
Shuai, Bing
Liu, Ai Qun
Wang, Gang
Keywords: Engineering::Computer science and engineering
Issue Date: 2020
Source: Ding, H., Jiang, X., Shuai, B., Liu, A. Q., & Wang, G. (2020). Semantic correlation promoted shape-variant context for segmentation. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 8877-8886. doi:10.1109/CVPR.2019.00909
Conference: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Abstract: Context is essential for semantic segmentation. Due to the diverse shapes of objects and their complex layout in various scene images, the spatial scales and shapes of contexts for different objects have very large variation. It is thus ineffective or inefficient to aggregate various context information from a predefined fixed region. In this work, we propose to generate a scale- and shape-variant semantic mask for each pixel to confine its contextual region. To this end, we first propose a novel paired convolution to infer the semantic correlation of the pair and based on that to generate a shape mask. Using the inferred spatial scope of the contextual region, we propose a shape-variant convolution, of which the receptive field is controlled by the shape mask that varies with the appearance of input. In this way, the proposed network aggregates the context information of a pixel from its semantic-correlated region instead of a predefined fixed region. Furthermore, this work also proposes a labeling denoising model to reduce wrong predictions caused by the noisy low-level features. Without bells and whistles, the proposed segmentation network achieves new state-of-the-arts consistently on the six public segmentation datasets.
ISBN: 978-1-7281-3294-5
DOI: 10.1109/CVPR.2019.00909
Schools: School of Electrical and Electronic Engineering 
Research Centres: Institute for Media Innovation (IMI) 
Rights: © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at:
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:IMI Conference Papers

Files in This Item:
File Description SizeFormat 
Semantic correlation promoted shape-variant context for segmentation.pdf1.46 MBAdobe PDFThumbnail

Citations 5

Updated on Jun 12, 2024

Web of ScienceTM
Citations 5

Updated on Oct 28, 2023

Page view(s)

Updated on Jun 20, 2024

Download(s) 20

Updated on Jun 20, 2024

Google ScholarTM




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