Learning to Calibrate for Reliable Visual Fire Detection

TL;DR

This paper introduces a novel differentiable ECE loss and a curriculum learning approach to improve the calibration and reliability of deep learning-based visual fire detection models, ensuring better uncertainty estimation.

Contribution

It proposes a differentiable ECE loss function combined with curriculum learning to enhance model calibration and uncertainty modeling in fire detection tasks.

Findings

Improved calibration of fire detection models demonstrated on DFAN and EdgeFireSmoke datasets.

Enhanced reliability of predictions through uncertainty-aware training.

Better balance between accuracy and confidence in fire detection models.

Abstract

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.