elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Global Message Passing in Networks via Task-driven Random Walks for Semantic Segmentation of Remote Sensing Images

Mou, LiChao and Hua, Yuansheng and Jin, Pu and Zhu, Xiao Xiang (2020) Global Message Passing in Networks via Task-driven Random Walks for Semantic Segmentation of Remote Sensing Images. In: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2-2020, pp. 533-540. ISPRS. ISPRS 2020, 2020-08-31 - 2020-09-02, Nice, France. doi: 10.5194/isprs-annals-V-2-2020-533-2020. ISSN 2194-9042.

[img] PDF
7MB

Official URL: https://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/V-2-2020/533/2020/

Abstract

The capability of globally modeling and reasoning about relations between image regions is crucial for complex scene understanding tasks such as semantic segmentation. Most current semantic segmentation methods fall back on deep convolutional neural networks (CNNs), while their use of convolutions with local receptive fields is typically inefficient at capturing long-range dependencies. Recent works on self-attention mechanisms and relational reasoning networks seek to address this issue by learning pairwise relations between each two entities and have showcased promising results. But such approaches have heavy computational and memory overheads, which is computationally infeasible for dense prediction tasks, particularly on large size images, i.e., aerial imagery. In this work, we propose an efficient method for global context modeling in which at each position, a sparse set of features, instead of all features, over the spatial domain are adaptively sampled and aggregated. We further devise a highly efficient instantiation of the proposed method, namely learning RANdom walK samplIng aNd feature aGgregation (RANKING). The proposed module is lightweight and general, which can be used in a plug-and-play fashion with the existing fully convolutional neural network (FCN) framework. To evaluate RANKING-equipped networks, we conduct experiments on two aerial scene parsing datasets, and the networks can achieve competitive results at significant low costs in terms of the computational and memory.

Item URL in elib:https://elib.dlr.de/139791/
Document Type:Conference or Workshop Item (Speech)
Title:Global Message Passing in Networks via Task-driven Random Walks for Semantic Segmentation of Remote Sensing Images
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Mou, LiChaoUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Hua, YuanshengUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Jin, PuUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Zhu, Xiao XiangUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Date:2020
Journal or Publication Title:ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In SCOPUS:Yes
In ISI Web of Science:Yes
Volume:2-2020
DOI:10.5194/isprs-annals-V-2-2020-533-2020
Page Range:pp. 533-540
Publisher:ISPRS
ISSN:2194-9042
Status:Published
Keywords:deep learning, global message passing, random walking, semantic segmentation, remote sensing
Event Title:ISPRS 2020
Event Location:Nice, France
Event Type:international Conference
Event Start Date:31 August 2020
Event End Date:2 September 2020
Organizer:ISPRS
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Earth Observation
DLR - Research area:Raumfahrt
DLR - Program:R EO - Earth Observation
DLR - Research theme (Project):R - Remote Sensing and Geo Research
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > EO Data Science
Deposited By: Bratasanu, Ion-Dragos
Deposited On:18 Dec 2020 13:34
Last Modified:24 Apr 2024 20:40

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.