Bidirectional Multi-scale Attention Networks for Semantic Segmentation of Oblique UAV Imagery
This work provides an incremental improvement for semantic segmentation of oblique UAV imagery, which is important for earth observation applications.
The paper addresses the challenge of large object scale variation in oblique UAV imagery for semantic segmentation. The proposed bidirectional multi-scale attention networks achieved a state-of-the-art mIoU score of 70.80% on the UAVid2020 dataset.
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%.