Deep learning-based object detection has demonstrated a significant presence in the practical applications of artificial intelligence. However, objects such as fire and smoke, pose challenges to object detection because of their non-solid and various shapes, and consequently difficult to truly meet requirements in practical fire prevention and control. In this paper, we propose that the distinctive fractal feature of self-similar in fire and smoke can relieve us from struggling with their various shapes. To our best knowledge, we are the first to discuss this problem. In order to evaluate the self-similarity of the fire and smoke and improve the precision of object detection, we design a semi-supervised method that use Hausdorff distance to describe the resemblance between instances. Besides, based on the concept of self-similar, we have devised a novel methodology for evaluating this particular task in a more equitable manner. We have meticulously designed our network architecture based on well-established and representative baseline networks such as YOLO and Faster R-CNN. Our experiments have been conducted on publicly available fire and smoke detection datasets, which we have thoroughly verified to ensure the validity of our approach. As a result, we have observed significant improvements in the detection accuracy.

翻译：基于深度学习的物体检测已在人工智能的实际应用中展现出显著优势。然而，火和烟雾等物体因其非固态和多变形态，给物体检测带来了挑战，因而难以真正满足实际防火防控的需求。本文提出，火和烟雾中独特的自相似分形特征可帮助我们摆脱对其多变形态的困扰。据我们所知，我们是首个探讨该问题的研究。为评估火和烟雾的自相似性并提升物体检测精度，我们设计了一种半监督方法，利用豪斯多夫距离描述实例间的相似度。此外，基于自相似概念，我们提出了一种更公平评估该特定任务的新方法。我们基于YOLO和Faster R-CNN等成熟且具有代表性的基线网络，精心设计了网络架构。实验在公开的火和烟雾检测数据集上进行，我们已验证了这些数据集的可靠性以确保方法的有效性。最终，检测精度取得了显著提升。