论文标题
实时识别分布样品，以进行安全关键的2D对象检测和保证金熵损失
Identifying Out-of-Distribution Samples in Real-Time for Safety-Critical 2D Object Detection with Margin Entropy Loss
论文作者
论文摘要
如今，卷积神经网络（CNN）经常被用于安全关键应用（例如自动驾驶或无人驾驶汽车（UAV））的基于视觉的感知堆栈。由于这些用例的安全要求，重要的是要知道CNN的局限性，因此要检测分布外（OOD）样品。在这项工作中，我们提出了一种方法，可以通过利用边距熵（ME）损失来启用2D对象检测。提出的方法易于实现，可以应用于大多数现有的对象检测体系结构。此外，我们引入了可分离性，作为用于检测对象检测中的OOD样品的度量。我们表明，使用标准置信度得分，接受ME损失训练的CNN明显优于OOD检测。同时，基础对象检测框架的运行时间保持不变，使ME损失成为启用OOD检测的强大工具。
Convolutional Neural Networks (CNNs) are nowadays often employed in vision-based perception stacks for safetycritical applications such as autonomous driving or Unmanned Aerial Vehicles (UAVs). Due to the safety requirements in those use cases, it is important to know the limitations of the CNN and, thus, to detect Out-of-Distribution (OOD) samples. In this work, we present an approach to enable OOD detection for 2D object detection by employing the margin entropy (ME) loss. The proposed method is easy to implement and can be applied to most existing object detection architectures. In addition, we introduce Separability as a metric for detecting OOD samples in object detection. We show that a CNN trained with the ME loss significantly outperforms OOD detection using standard confidence scores. At the same time, the runtime of the underlying object detection framework remains constant rendering the ME loss a powerful tool to enable OOD detection.
