Identifying Out-of-Distribution Samples in Real-Time for Safety-Critical 2D Object Detection with Margin Entropy Loss

TL;DR

This paper introduces a margin entropy loss-based method for real-time out-of-distribution detection in 2D object detection, improving safety in autonomous systems by outperforming confidence-based methods without impacting runtime.

Contribution

It proposes a novel, easy-to-implement margin entropy loss approach and a new Separability metric for effective OOD detection in existing object detection models.

Findings

ME loss significantly improves OOD detection accuracy

The method maintains constant runtime performance

Outperforms standard confidence score methods

Abstract

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.