Please use this identifier to cite or link to this item:
Title: Boundary-aware feature propagation for scene segmentation
Authors: Ding, Henghui
Jiang, Xudong
Liu, Ai Qun
Thalmann, Nadia Magnenat
Wang, Gang
Keywords: Engineering::Computer science and engineering
Issue Date: 2019
Source: Ding, H., Jiang, X., Liu, A. Q., Thalmann, N. M., & Wang, G. (2019). Boundary-aware feature propagation for scene segmentation. Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV), 6818-6828. doi:10.1109/ICCV.2019.00692
metadata.dc.contributor.conference: 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
Abstract: In this work, we address the challenging issue of scene segmentation. To increase the feature similarity of the same object while keeping the feature discrimination of different objects, we explore to propagate information throughout the image under the control of objects' boundaries. To this end, we first propose to learn the boundary as an additional semantic class to enable the network to be aware of the boundary layout. Then, we propose unidirectional acyclic graphs (UAGs) to model the function of undirected cyclic graphs (UCGs), which structurize the image via building graphic pixel-by-pixel connections, in an efficient and effective way. Furthermore, we propose a boundary-aware feature propagation (BFP) module to harvest and propagate the local features within their regions isolated by the learned boundaries in the UAG-structured image. The proposed BFP is capable of splitting the feature propagation into a set of semantic groups via building strong connections among the same segment region but weak connections between different segment regions. Without bells and whistles, our approach achieves new state-of-the-art segmentation performance on three challenging semantic segmentation datasets, i.e., PASCAL-Context, CamVid, and Cityscapes.
ISBN: 9781728148038
DOI: 10.1109/ICCV.2019.00692
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 
Ding_Boundary-Aware_Feature_Propagation_for_Scene_Segmentation_ICCV_2019_paper.pdfpaper1.62 MBAdobe PDFThumbnail

Citations 5

Updated on May 28, 2023

Web of ScienceTM
Citations 5

Updated on May 31, 2023

Page view(s)

Updated on Jun 2, 2023

Download(s) 20

Updated on Jun 2, 2023

Google ScholarTM




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