Identifying Out-of-Distribution Samples in Real-Time for Safety-Critical 2D Object Detection with Margin Entropy Loss
Published in ECCV UNCV Workshop, 2022
Recommended citation: Yannik Blei, Nicolas Jourdan, and Nils Gahlert. Identifying Out-of-Distribution Samples in Real-Time for Safety-Critical 2D Object Detection with Margin Entropy Loss. arXiv:2209.00364 [cs]. Sept. 2022 https://arxiv.org/pdf/2209.00364.pdf
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.