The detection of small objects is a challenging task in computer vision. Conventional object detection methods have difficulty in finding the balance between high detection and low false alarm rates. In the literature, some methods have addressed this issue by enhancing the feature map responses, but without guaranteeing robustness with respect to the number of false alarms induced by background elements. To tackle this problem, we introduce an $\textit{a contrario}$ decision criterion into the learning process to take into account the unexpectedness of small objects. This statistic criterion enhances the feature map responses while controlling the number of false alarms (NFA) and can be integrated into any semantic segmentation neural network. Our add-on NFA module not only allows us to obtain competitive results for small target and crack detection tasks respectively, but also leads to more robust and interpretable results.

翻译：小目标检测是计算机视觉中的一项挑战性任务。传统目标检测方法难以在高检测率与低误报率之间找到平衡。现有文献中，部分方法通过增强特征图响应来解决该问题，但未能保证对背景元素引发的误报数量具有鲁棒性。为解决此问题，我们将 $\textit{a contrario}$ 决策准则引入学习过程，以考虑小目标的意外性。该统计准则在增强特征图响应的同时控制误报数量（NFA），并可集成至任意语义分割神经网络中。我们的附加NFA模块不仅能在小目标检测和裂缝检测任务中分别获得具有竞争力的结果，还能带来更鲁棒且可解释的结果。