Bidirectional Multi-scale Attention Networks for Semantic Segmentation of Oblique UAV Imagery

TL;DR

This paper introduces bidirectional multi-scale attention networks for semantic segmentation of oblique UAV imagery, effectively handling large scale variations and achieving state-of-the-art results on UAV datasets.

Contribution

The paper proposes a novel bidirectional multi-scale attention mechanism to improve feature extraction in oblique UAV imagery segmentation.

Findings

Achieved a state-of-the-art mIoU of 70.80% on UAVid2020 dataset.

Demonstrated improved segmentation performance over existing methods.

Validated the effectiveness of multi-scale feature fusion in aerial imagery.

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%.