Semi-Supervised Domain Adaptation for Wildfire Detection
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_ | 1866910396024094720 |
|---|---|
| author | Jang, JooYoung Cha, Youngseo Kim, Jisu Lee, SooHyung Lee, Geonu Cho, Minkook Hwang, Young Kwak, Nojun |
| author_facet | Jang, JooYoung Cha, Youngseo Kim, Jisu Lee, SooHyung Lee, Geonu Cho, Minkook Hwang, Young Kwak, Nojun |
| contents | Recently, both the frequency and intensity of wildfires have increased worldwide, primarily due to climate change. In this paper, we propose a novel protocol for wildfire detection, leveraging semi-supervised Domain Adaptation for object detection, accompanied by a corresponding dataset designed for use by both academics and industries. Our dataset encompasses 30 times more diverse labeled scenes for the current largest benchmark wildfire dataset, HPWREN, and introduces a new labeling policy for wildfire detection. Inspired by CoordConv, we propose a robust baseline, Location-Aware Object Detection for Semi-Supervised Domain Adaptation (LADA), utilizing a teacher-student based framework capable of extracting translational variance features characteristic of wildfires. With only using 1% target domain labeled data, our framework significantly outperforms our source-only baseline by a notable margin of 3.8% in mean Average Precision on the HPWREN wildfire dataset. Our dataset is available at https://github.com/BloomBerry/LADA. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_01842 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Semi-Supervised Domain Adaptation for Wildfire Detection Jang, JooYoung Cha, Youngseo Kim, Jisu Lee, SooHyung Lee, Geonu Cho, Minkook Hwang, Young Kwak, Nojun Computer Vision and Pattern Recognition Recently, both the frequency and intensity of wildfires have increased worldwide, primarily due to climate change. In this paper, we propose a novel protocol for wildfire detection, leveraging semi-supervised Domain Adaptation for object detection, accompanied by a corresponding dataset designed for use by both academics and industries. Our dataset encompasses 30 times more diverse labeled scenes for the current largest benchmark wildfire dataset, HPWREN, and introduces a new labeling policy for wildfire detection. Inspired by CoordConv, we propose a robust baseline, Location-Aware Object Detection for Semi-Supervised Domain Adaptation (LADA), utilizing a teacher-student based framework capable of extracting translational variance features characteristic of wildfires. With only using 1% target domain labeled data, our framework significantly outperforms our source-only baseline by a notable margin of 3.8% in mean Average Precision on the HPWREN wildfire dataset. Our dataset is available at https://github.com/BloomBerry/LADA. |
| title | Semi-Supervised Domain Adaptation for Wildfire Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.01842 |