Attention based network for remote sensing scene classification

Shaoteng Liu; Qi Wang; Xuelong Li

doi:10.1109/IGARSS.2018.8519232

Attention based network for remote sensing scene classification

Shaoteng Liu
, Qi Wang
, Xuelong Li

School of Artificial Intelligence, OPtics and Electronics

Northwestern Polytechnical University Xian
CAS - Xi'an Institute of Optics and Precision Mechanics
University of Chinese Academy of Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

12 Scopus citations

Abstract

Scene classification of very high resolution remote sensing images is becoming more and more important because of its wide range of applications. However, previous works are mainly based on handcrafted features which do not have enough adaptability and expression ability. In this paper, inspired by the attention mechanism of human visual system, we propose a novel attention based network (AttNet) for scene classification. It can focus selectively on some key areas of images so that it can abandon redundant information. Essentially, AttNet gives a way to readjust the signal of supervision, and it is one of the first successful attempts on visual attention for remote sensing scene classification. Our method is evaluated on the UC Merced Land-Use Dataset, in comparison with some state-of-the-art methods. The experimental result shows that the proposed method makes a great improvement on both convergence speed and classification accuracy, and it also shows the effectiveness of visual attention for this task.

Original language	English
Title of host publication	2018 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	4740-4743
Number of pages	4
ISBN (Electronic)	9781538671504
DOIs	https://doi.org/10.1109/IGARSS.2018.8519232
State	Published - 31 Oct 2018
Event	38th Annual IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 - Valencia, Spain Duration: 22 Jul 2018 → 27 Jul 2018

Publication series

Name	International Geoscience and Remote Sensing Symposium (IGARSS)
Volume	2018-July
ISSN (Print)	2153-6996
ISSN (Electronic)	2153-7003

Conference

Conference	38th Annual IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018
Country/Territory	Spain
City	Valencia
Period	22/07/18 → 27/07/18

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 15 Life on Land

Keywords

Convolutional neural networks
Deep learning
Long short-term memory
Remote sensing
Scene classification
Visual attention

Access to Document

10.1109/IGARSS.2018.8519232

Cite this

Liu, S., Wang, Q., & Li, X. (2018). Attention based network for remote sensing scene classification. In 2018 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 - Proceedings (pp. 4740-4743). Article 8519232 (International Geoscience and Remote Sensing Symposium (IGARSS) ; Vol. 2018-July). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IGARSS.2018.8519232

@inproceedings{7bb2426929274995904440f053b949bb,

title = "Attention based network for remote sensing scene classification",

abstract = "Scene classification of very high resolution remote sensing images is becoming more and more important because of its wide range of applications. However, previous works are mainly based on handcrafted features which do not have enough adaptability and expression ability. In this paper, inspired by the attention mechanism of human visual system, we propose a novel attention based network (AttNet) for scene classification. It can focus selectively on some key areas of images so that it can abandon redundant information. Essentially, AttNet gives a way to readjust the signal of supervision, and it is one of the first successful attempts on visual attention for remote sensing scene classification. Our method is evaluated on the UC Merced Land-Use Dataset, in comparison with some state-of-the-art methods. The experimental result shows that the proposed method makes a great improvement on both convergence speed and classification accuracy, and it also shows the effectiveness of visual attention for this task.",

keywords = "Convolutional neural networks, Deep learning, Long short-term memory, Remote sensing, Scene classification, Visual attention",

author = "Shaoteng Liu and Qi Wang and Xuelong Li",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 38th Annual IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 ; Conference date: 22-07-2018 Through 27-07-2018",

year = "2018",

month = oct,

day = "31",

doi = "10.1109/IGARSS.2018.8519232",

language = "英语",

series = "International Geoscience and Remote Sensing Symposium (IGARSS) ",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "4740--4743",

booktitle = "2018 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 - Proceedings",

}

Liu, S, Wang, Q & Li, X 2018, Attention based network for remote sensing scene classification. in 2018 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 - Proceedings., 8519232, International Geoscience and Remote Sensing Symposium (IGARSS) , vol. 2018-July, Institute of Electrical and Electronics Engineers Inc., pp. 4740-4743, 38th Annual IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018, Valencia, Spain, 22/07/18. https://doi.org/10.1109/IGARSS.2018.8519232

Attention based network for remote sensing scene classification. / Liu, Shaoteng; Wang, Qi; Li, Xuelong.
2018 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2018. p. 4740-4743 8519232 (International Geoscience and Remote Sensing Symposium (IGARSS) ; Vol. 2018-July).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Attention based network for remote sensing scene classification

AU - Liu, Shaoteng

AU - Wang, Qi

AU - Li, Xuelong

PY - 2018/10/31

Y1 - 2018/10/31

N2 - Scene classification of very high resolution remote sensing images is becoming more and more important because of its wide range of applications. However, previous works are mainly based on handcrafted features which do not have enough adaptability and expression ability. In this paper, inspired by the attention mechanism of human visual system, we propose a novel attention based network (AttNet) for scene classification. It can focus selectively on some key areas of images so that it can abandon redundant information. Essentially, AttNet gives a way to readjust the signal of supervision, and it is one of the first successful attempts on visual attention for remote sensing scene classification. Our method is evaluated on the UC Merced Land-Use Dataset, in comparison with some state-of-the-art methods. The experimental result shows that the proposed method makes a great improvement on both convergence speed and classification accuracy, and it also shows the effectiveness of visual attention for this task.

AB - Scene classification of very high resolution remote sensing images is becoming more and more important because of its wide range of applications. However, previous works are mainly based on handcrafted features which do not have enough adaptability and expression ability. In this paper, inspired by the attention mechanism of human visual system, we propose a novel attention based network (AttNet) for scene classification. It can focus selectively on some key areas of images so that it can abandon redundant information. Essentially, AttNet gives a way to readjust the signal of supervision, and it is one of the first successful attempts on visual attention for remote sensing scene classification. Our method is evaluated on the UC Merced Land-Use Dataset, in comparison with some state-of-the-art methods. The experimental result shows that the proposed method makes a great improvement on both convergence speed and classification accuracy, and it also shows the effectiveness of visual attention for this task.

KW - Convolutional neural networks

KW - Deep learning

KW - Long short-term memory

KW - Remote sensing

KW - Scene classification

KW - Visual attention

UR - https://www.scopus.com/pages/publications/85064157076

U2 - 10.1109/IGARSS.2018.8519232

DO - 10.1109/IGARSS.2018.8519232

M3 - 会议稿件

AN - SCOPUS:85064157076

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 4740

EP - 4743

BT - 2018 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 38th Annual IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018

Y2 - 22 July 2018 through 27 July 2018

ER -

Attention based network for remote sensing scene classification

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this