让火灾检测模型学会自知优劣，提升判断可靠性。
Learning to Calibrate for Reliable Visual Fire Detection
- 用可微分的校准误差损失优化模型置信度
- 在两个数据集上同时提升准确率与不确定性可信度
- 适合需要高可靠性决策的安防场景使用
火灾具有突发性和破坏性，早期检测对保障人身安全和财产至关重要。随着深度学习的发展，计算机视觉在火灾检测中的应用显著提升。然而，深度学习模型常表现出过度自信，现有工作多关注分类性能提升，较少关注不确定性建模。为此，我们提出将期望校准误差（ECE）这一不确定性度量转化为可微分的ECE损失函数，并与交叉熵损失结合，指导多类火灾检测模型的训练。为进一步平衡分类准确率与可靠决策，引入基于课程学习的方法，动态调整ECE损失权重。在两个常用多类火灾检测数据集DFAN和EdgeFireSmoke上进行了大量实验，验证了所提不确定性建模方法的有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。