Abstract
Abstract. Semantic segmentation for aerial platforms has been one of the fundamental scene understanding task for the earth observation. Most of the semantic segmentation research focused on scenes captured in nadir view, in which objects have relatively smaller scale variation compared with scenes captured in oblique view. The huge scale variation of objects in oblique images limits the performance of deep neural networks (DNN) that process images in a single scale fashion. In order to tackle the scale variation issue, in this paper, we propose the novel bidirectional multi-scale attention networks, which fuse features from multiple scales bidirectionally for more adaptive and effective feature extraction. The experiments are conducted on the UAVid2020 dataset and have shown the effectiveness of our method. Our model achieved the state-of-the-art (SOTA) result with a mean intersection over union (mIoU) score of 70.80%.
Highlights
Semantic segmentation has been one of the most fundamental research tasks for scene understanding
We propose the bidirectional multi-scale attention networks (BiMSANet) to address the multi-scale problem in the semantic segmentation task
We have proposed a novel bidirectional multi-scale attention networks to handle the multi-scale problem for the semantic segmentation task
Summary
Semantic segmentation has been one of the most fundamental research tasks for scene understanding. A simple strategy is to apply multiscale inference (Zhao et al, 2017), i.e., a well-trained deep neural networks predict the score maps of the same image in multiple different scales, and the score maps are averaged to determine the final label prediction. The second strategy is to design a multi-scale feature extractor module in the middle of the deep neural networks (Zhao et al, 2017, Chen et al, 2017, Chen et al, 2018, Yuan and Wang, 2018, Lyu et al, 2020). We have achieved state-of-the-art result on the UAVid2020 benchmark, and the code will be made public
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call