About this document
Gully Erosion Monitoring via AI Techniques by Malu Malu is a document available to read on EtoBox.
This paper presents a novel semi-supervised semantic segmentation method for monitoring gully erosion, utilizing a boundary-guided pseudo-label generation strategy and an adaptive loss function to improve the reliability of monitoring results. The method effectively combines historical labeled data with the latest unlabeled monitoring data to generate high-quality pseudo-labels while addressing the challenges of noise in pseudo-labels. Experimental results demonstrate that this approach outperforms existing
- Author
- Malu Malu
- Language
- EN