We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Reliable Label-Supervised Pixel Attention Mechanism for Weakly Supervised Building Segmentation in UAV Imagery.
- Authors
Chen, Jun; Xu, Weifeng; Yu, Yang; Peng, Chengli; Gong, Wenping
- Abstract
Building segmentation for Unmanned Aerial Vehicle (UAV) imagery usually requires pixel-level labels, which are time-consuming and expensive to collect. Weakly supervised semantic segmentation methods for image-level labeling have recently achieved promising performance in natural scenes, but there have been few studies on UAV remote sensing imagery. In this paper, we propose a reliable label-supervised pixel attention mechanism for building segmentation in UAV imagery. Our method is based on the class activation map. However, classification networks tend to capture discriminative parts of the object and are insensitive to over-activation; therefore, class activation maps cannot directly guide segmentation network training. To overcome these challenges, we first design a Pixel Attention Module that captures rich contextual relationships, which can further mine more discriminative regions, in order to obtain a modified class activation map. Then, we use the initial seeds generated by the classification network to synthesize reliable labels. Finally, we design a reliable label loss, which is defined as the sum of the pixel-level differences between the reliable labels and the modified class activation map. Notably, the reliable label loss can handle over-activation. The preceding steps can significantly improve the quality of the pseudo-labels. Experiments on our home-made UAV data set indicate that our method can achieve 88.8% mIoU on the test set, outperforming previous state-of-the-art weakly supervised methods.
- Subjects
PIXELS; DRONE aircraft; REMOTE sensing; LABEL design; LANDSAT satellites; THEMATIC mapper satellite
- Publication
Remote Sensing, 2022, Vol 14, Issue 13, p3196
- ISSN
2072-4292
- Publication type
Article
- DOI
10.3390/rs14133196