Lightweight salient object detection in optical remote sensing images via feature correlation
Salient object detection in optical remote sensing images (ORSI-SOD) has been widely explored for understanding ORSIs. However, previous methods focus mainly on improving the detection accuracy while neglecting the cost in memory and computation, which may hinder their real-world applications. In...
Saved in:
Main Authors: | , , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/162649 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-162649 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1626492022-11-02T02:06:26Z Lightweight salient object detection in optical remote sensing images via feature correlation Li, Gongyang Liu, Zhi Bai, Zhen Lin, Weisi Ling, Haibin School of Computer Science and Engineering Engineering::Computer science and engineering Cross-Layer Correlation Dense Lightweight Refinement Block Salient object detection in optical remote sensing images (ORSI-SOD) has been widely explored for understanding ORSIs. However, previous methods focus mainly on improving the detection accuracy while neglecting the cost in memory and computation, which may hinder their real-world applications. In this paper, we propose a novel lightweight ORSI-SOD solution, named CorrNet, to address these issues. In CorrNet, we first lighten the backbone (VGG-16) and build a lightweight subnet for feature extraction. Then, following the coarse-to-fine strategy, we generate an initial coarse saliency map from high-level semantic features in a Correlation Module (CorrM). The coarse saliency map serves as the location guidance for low-level features. In CorrM, we mine the object location information between high-level semantic features through the cross-layer correlation operation. Finally, based on low-level detailed features, we refine the coarse saliency map in the refinement subnet equipped with Dense Lightweight Refinement Blocks, and produce the final fine saliency map. By reducing the parameters and computations of each component, CorrNet ends up having only 4.09M parameters and running with 21.09G FLOPs. Experimental results on two public datasets demonstrate that our lightweight CorrNet achieves competitive or even better performance compared with 26 state-of-the-art methods (including 16 large CNN-based methods and 2 lightweight methods), and meanwhile enjoys the clear memory and run time efficiency. The code and results of our method are available at https://github.com/MathLee/CorrNet. Ministry of Education (MOE) This work was supported in part by the National Natural Science Foundation of China under Grant 62171269, in part by the China Scholarship Council under Grant 202006890079, and in part by the Singapore Ministry of Education Tier-2 Fund under Grant MOE2016-T2-2- 057(S). 2022-11-02T02:06:26Z 2022-11-02T02:06:26Z 2022 Journal Article Li, G., Liu, Z., Bai, Z., Lin, W. & Ling, H. (2022). Lightweight salient object detection in optical remote sensing images via feature correlation. IEEE Transactions On Geoscience and Remote Sensing, 60. https://dx.doi.org/10.1109/TGRS.2022.3145483 0196-2892 https://hdl.handle.net/10356/162649 10.1109/TGRS.2022.3145483 2-s2.0-85123706916 60 en MOE2016-T2-2- 057(S) IEEE Transactions on Geoscience and Remote Sensing © 2022 IEEE. All rights reserved. |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Computer science and engineering Cross-Layer Correlation Dense Lightweight Refinement Block |
spellingShingle |
Engineering::Computer science and engineering Cross-Layer Correlation Dense Lightweight Refinement Block Li, Gongyang Liu, Zhi Bai, Zhen Lin, Weisi Ling, Haibin Lightweight salient object detection in optical remote sensing images via feature correlation |
description |
Salient object detection in optical remote sensing images (ORSI-SOD) has been
widely explored for understanding ORSIs. However, previous methods focus mainly
on improving the detection accuracy while neglecting the cost in memory and
computation, which may hinder their real-world applications. In this paper, we
propose a novel lightweight ORSI-SOD solution, named CorrNet, to address these
issues. In CorrNet, we first lighten the backbone (VGG-16) and build a
lightweight subnet for feature extraction. Then, following the coarse-to-fine
strategy, we generate an initial coarse saliency map from high-level semantic
features in a Correlation Module (CorrM). The coarse saliency map serves as the
location guidance for low-level features. In CorrM, we mine the object location
information between high-level semantic features through the cross-layer
correlation operation. Finally, based on low-level detailed features, we refine
the coarse saliency map in the refinement subnet equipped with Dense
Lightweight Refinement Blocks, and produce the final fine saliency map. By
reducing the parameters and computations of each component, CorrNet ends up
having only 4.09M parameters and running with 21.09G FLOPs. Experimental
results on two public datasets demonstrate that our lightweight CorrNet
achieves competitive or even better performance compared with 26
state-of-the-art methods (including 16 large CNN-based methods and 2
lightweight methods), and meanwhile enjoys the clear memory and run time
efficiency. The code and results of our method are available at
https://github.com/MathLee/CorrNet. |
author2 |
School of Computer Science and Engineering |
author_facet |
School of Computer Science and Engineering Li, Gongyang Liu, Zhi Bai, Zhen Lin, Weisi Ling, Haibin |
format |
Article |
author |
Li, Gongyang Liu, Zhi Bai, Zhen Lin, Weisi Ling, Haibin |
author_sort |
Li, Gongyang |
title |
Lightweight salient object detection in optical remote sensing images via feature correlation |
title_short |
Lightweight salient object detection in optical remote sensing images via feature correlation |
title_full |
Lightweight salient object detection in optical remote sensing images via feature correlation |
title_fullStr |
Lightweight salient object detection in optical remote sensing images via feature correlation |
title_full_unstemmed |
Lightweight salient object detection in optical remote sensing images via feature correlation |
title_sort |
lightweight salient object detection in optical remote sensing images via feature correlation |
publishDate |
2022 |
url |
https://hdl.handle.net/10356/162649 |
_version_ |
1749179242859462656 |