Log In Sign Up

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

by   Ye Lyu, et al.

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


page 1

page 3

page 4

page 5

page 6

page 7

page 8


The UAVid Dataset for Video Semantic Segmentation

Video semantic segmentation has been one of the research focus in comput...

Multi-Class Segmentation from Aerial Views using Recursive Noise Diffusion

Semantic segmentation from aerial views is a vital task for autonomous d...

SaNet: Scale-aware neural Network for Parsing Multiple Spatial Resolution Aerial Images

Assigning the geospatial objects of aerial images with categorical infor...

Segmenting Ships in Satellite Imagery With Squeeze and Excitation U-Net

The ship-detection task in satellite imagery presents significant obstac...

Dilated SpineNet for Semantic Segmentation

Scale-permuted networks have shown promising results on object bounding ...

Hierarchical Multi-Scale Attention for Semantic Segmentation

Multi-scale inference is commonly used to improve the results of semanti...

Interactive Segmentation of Radiance Fields

Radiance Fields (RF) are popular to represent casually-captured scenes f...

Code Repositories


This is the repository for bidirectional multi-scale attention networks.

view repo