PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation

Li, Xiangtai, He, Hao, Li, Xia, Li, Duo, Cheng, Guangliang ORCID: 0000-0001-8686-9513, Shi, Jianping, Weng, Lubin, Tong, Yunhai and Lin, Zhouchen (2021) PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation. In: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021-6-20 - 2021-6-25.

Access the full-text of this item by clicking on the Open Access link.

Official URL: http://dx.doi.org/10.1109/cvpr46437.2021.00420

Abstract

Aerial Image Segmentation is a particular semantic segmentation problem and has several challenging characteristics that general semantic segmentation does not have. There are two critical issues: The one is an extremely foreground-background imbalanced distribution, and the other is multiple small objects along with the complex background. Such problems make the recent dense affinity context modeling perform poorly even compared with baselines due to over-introduced background context. To handle these problems, we propose a point-wise affinity propagation module based on the Feature Pyramid Network (FPN) framework, named PointFlow. Rather than dense affinity learning, a sparse affinity map is generated upon selected points between the adjacent features, which reduces the noise introduced by the background while keeping efficiency. In particular, we design a dual point matcher to select points from the salient area and object boundaries, respectively. Experimental results on three different aerial segmentation datasets suggest that the proposed method is more effective and efficient than state-of-the-art general semantic segmentation methods. Especially, our methods achieve the best speed and accuracy trade-off on three aerial benchmarks. Further experiments on three general semantic segmentation datasets prove the generality of our method. Code and models are made available (https://github.com/lxtGH/PFSegNets).

Item Type:	Conference or Workshop Item (Unspecified)
Divisions:	Faculty of Science and Engineering > School of Electrical Engineering, Electronics and Computer Science
Depositing User:	Symplectic Admin
Date Deposited:	14 Mar 2023 09:31
Last Modified:	24 Apr 2024 11:30
DOI:	10.1109/cvpr46437.2021.00420
Open Access URL:	https://openaccess.thecvf.com/content/CVPR2021/pap...
Related URLs:	Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3169000