Learning to Calibrate for Reliable Visual Fire Detection
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913690723287040 |
|---|---|
| author | Zhang, Ziqi Zhou, Xiuzhuang Gong, Xiangyang |
| author_facet | Zhang, Ziqi Zhou, Xiuzhuang Gong, Xiangyang |
| contents | Fire is characterized by its sudden onset and destructive power, making early fire detection crucial for ensuring human safety and protecting property. With the advancement of deep learning, the application of computer vision in fire detection has significantly improved. However, deep learning models often exhibit a tendency toward overconfidence, and most existing works focus primarily on enhancing classification performance, with limited attention given to uncertainty modeling. To address this issue, we propose transforming the Expected Calibration Error (ECE), a metric for measuring uncertainty, into a differentiable ECE loss function. This loss is then combined with the cross-entropy loss to guide the training process of multi-class fire detection models. Additionally, to achieve a good balance between classification accuracy and reliable decision, we introduce a curriculum learning-based approach that dynamically adjusts the weight of the ECE loss during training. Extensive experiments are conducted on two widely used multi-class fire detection datasets, DFAN and EdgeFireSmoke, validating the effectiveness of our uncertainty modeling method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_09872 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning to Calibrate for Reliable Visual Fire Detection Zhang, Ziqi Zhou, Xiuzhuang Gong, Xiangyang Computer Vision and Pattern Recognition Machine Learning Fire is characterized by its sudden onset and destructive power, making early fire detection crucial for ensuring human safety and protecting property. With the advancement of deep learning, the application of computer vision in fire detection has significantly improved. However, deep learning models often exhibit a tendency toward overconfidence, and most existing works focus primarily on enhancing classification performance, with limited attention given to uncertainty modeling. To address this issue, we propose transforming the Expected Calibration Error (ECE), a metric for measuring uncertainty, into a differentiable ECE loss function. This loss is then combined with the cross-entropy loss to guide the training process of multi-class fire detection models. Additionally, to achieve a good balance between classification accuracy and reliable decision, we introduce a curriculum learning-based approach that dynamically adjusts the weight of the ECE loss during training. Extensive experiments are conducted on two widely used multi-class fire detection datasets, DFAN and EdgeFireSmoke, validating the effectiveness of our uncertainty modeling method. |
| title | Learning to Calibrate for Reliable Visual Fire Detection |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2502.09872 |