Weak Labeling for Cropland Mapping in Africa
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911756968787968 |
|---|---|
| author | Hacheme, Gilles Quentin Zaytar, Akram Tadesse, Girmaw Abebe Robinson, Caleb Dodhia, Rahul Ferres, Juan M. Lavista Wood, Stephen |
| author_facet | Hacheme, Gilles Quentin Zaytar, Akram Tadesse, Girmaw Abebe Robinson, Caleb Dodhia, Rahul Ferres, Juan M. Lavista Wood, Stephen |
| contents | Cropland mapping can play a vital role in addressing environmental, agricultural, and food security challenges. However, in the context of Africa, practical applications are often hindered by the limited availability of high-resolution cropland maps. Such maps typically require extensive human labeling, thereby creating a scalability bottleneck. To address this, we propose an approach that utilizes unsupervised object clustering to refine existing weak labels, such as those obtained from global cropland maps. The refined labels, in conjunction with sparse human annotations, serve as training data for a semantic segmentation network designed to identify cropland areas. We conduct experiments to demonstrate the benefits of the improved weak labels generated by our method. In a scenario where we train our model with only 33 human-annotated labels, the F_1 score for the cropland category increases from 0.53 to 0.84 when we add the mined negative labels. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_07014 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Weak Labeling for Cropland Mapping in Africa Hacheme, Gilles Quentin Zaytar, Akram Tadesse, Girmaw Abebe Robinson, Caleb Dodhia, Rahul Ferres, Juan M. Lavista Wood, Stephen Computer Vision and Pattern Recognition Artificial Intelligence Cropland mapping can play a vital role in addressing environmental, agricultural, and food security challenges. However, in the context of Africa, practical applications are often hindered by the limited availability of high-resolution cropland maps. Such maps typically require extensive human labeling, thereby creating a scalability bottleneck. To address this, we propose an approach that utilizes unsupervised object clustering to refine existing weak labels, such as those obtained from global cropland maps. The refined labels, in conjunction with sparse human annotations, serve as training data for a semantic segmentation network designed to identify cropland areas. We conduct experiments to demonstrate the benefits of the improved weak labels generated by our method. In a scenario where we train our model with only 33 human-annotated labels, the F_1 score for the cropland category increases from 0.53 to 0.84 when we add the mined negative labels. |
| title | Weak Labeling for Cropland Mapping in Africa |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2401.07014 |