English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Convolutional Neural Networks (CNNs) are nowadays often employed invision-based perception stacks for safetycritical applications such asautonomous driving or Unmanned Aerial Vehicles (UAVs). Due to the safetyrequirements in those use cases, it is important to know the limitations of theCNN and, thus, to detect Out-of-Distribution (OOD) samples. In this work, wepresent an approach to enable OOD detection for 2D object detection byemploying the margin entropy (ME) loss. The proposed method is easy toimplement and can be applied to most existing object detection architectures.In addition, we introduce Separability as a metric for detecting OOD samples inobject detection. We show that a CNN trained with the ME loss significantlyoutperforms OOD detection using standard confidence scores. At the same time,the runtime of the underlying object detection framework remains constantrendering the ME loss a powerful tool to enable OOD detection.

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