Semantic Attention and Scale Complementary Network for Instance Segmentation in Remote Sensing Images.pdf (24.19 MB)
Download file

Semantic Attention and Scale Complementary Network for Instance Segmentation in Remote Sensing Images

Download (24.19 MB)
journal contribution
posted on 05.08.2021, 13:23 by T Zhang, X Zhang, P Zhu, X Tang, C Li, LC Jiao, Huiyu Zhou
In this paper, we focus on the challenging multi-category instance segmentation problem in remote sensing images(RSIs), which aims at predicting the categories of all instances and localizing them with pixel-level masks. Although many land-mark frameworks have demonstrated promising performance in instance segmentation, the complexity in the background and scale variability instances still remain challenging for in-stance segmentation of RSIs. To address the above problems, we propose an end-to-end multi-category instance segmentation model, namely Semantic Attention and Scale Complementary Network, which mainly consists of a Semantic Attention (SEA)module and a Scale Complementary Mask Branch (SCMB).The SEA module contains a simple fully convolutional semantic segmentation branch with extra supervision to strengthen the activation of interest instances on the feature map and reduce the background noise’s interference. To handle the under-segmentation of geospatial instances with large varying scales, we design the SCMB that extends the original single-scale mask branch to trident mask branches and introduces complementary mask supervision at different scales to sufficiently leverage the multi-scale information. We conduct comprehensive experiments to evaluate the effectiveness of our proposed method on the iSAID dataset and the NWPU Instance Segmentation dataset and achieve promising performance.

Funding

This work was supported by the National Natural Science Foundationof China (Nos. 61772400, 61772399, 61871306), and the 111 Project (No.B07048). H. Zhou was supported by UK EPSRC under Grant EP/N011074/1,Royal Society-Newton Advanced Fellowship under Grant NA160342, andEuropean Union’s Horizon 2020 research and innovation program under theMarie-Sklodowska-Curie grant agreement No 720325.

History

Author affiliation

School of Informatics

Version

AM (Accepted Manuscript)

Published in

IEEE Transactions on Cybernetics

Publisher

Institute of Electrical and Electronics Engineers

issn

2168-2267

eissn

2168-2267

Acceptance date

28/06/2021

Copyright date

2021

Available date

05/08/2021

Publisher DOI

Language

en