Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/162649
Full metadata record
DC FieldValueLanguage
dc.contributor.authorLi, Gongyangen_US
dc.contributor.authorLiu, Zhien_US
dc.contributor.authorBai, Zhenen_US
dc.contributor.authorLin, Weisien_US
dc.contributor.authorLing, Haibinen_US
dc.date.accessioned2022-11-02T02:06:26Z-
dc.date.available2022-11-02T02:06:26Z-
dc.date.issued2022-
dc.identifier.citationLi, 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.2022.3145483en_US
dc.identifier.issn0196-2892en_US
dc.identifier.urihttps://hdl.handle.net/10356/162649-
dc.description.abstractSalient 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.en_US
dc.description.sponsorshipMinistry of Education (MOE)en_US
dc.language.isoenen_US
dc.relationMOE2016-T2-2- 057(S)en_US
dc.relation.ispartofIEEE Transactions on Geoscience and Remote Sensingen_US
dc.rights© 2022 IEEE. All rights reserved.en_US
dc.subjectEngineering::Computer science and engineeringen_US
dc.titleLightweight salient object detection in optical remote sensing images via feature correlationen_US
dc.typeJournal Articleen
dc.contributor.schoolSchool of Computer Science and Engineeringen_US
dc.identifier.doi10.1109/TGRS.2022.3145483-
dc.identifier.scopus2-s2.0-85123706916-
dc.identifier.volume60en_US
dc.subject.keywordsCross-Layer Correlationen_US
dc.subject.keywordsDense Lightweight Refinement Blocken_US
dc.description.acknowledgementThis 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).en_US
item.grantfulltextnone-
item.fulltextNo Fulltext-
Appears in Collections:SCSE Journal Articles

SCOPUSTM   
Citations 20

7
Updated on Feb 4, 2023

Web of ScienceTM
Citations 20

6
Updated on Feb 4, 2023

Page view(s)

17
Updated on Feb 4, 2023

Google ScholarTM

Check

Altmetric


Plumx

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