BAM: Box Abstraction Monitors for Real-time OoD Detection in Object Detection

arXiv:2403.18373v1 Announce Type: new
Abstract: Out-of-distribution (OoD) detection techniques for deep neural networks (DNNs) become crucial thanks to their filtering of abnormal inputs, especially when DNNs are used in safety-critical applications and interact with an open and dynamic environment. Nevertheless, integrating OoD detection into state-of-the-art (SOTA) object detection DNNs poses significant challenges, partly due to the complexity introduced by the SOTA OoD construction methods, which require the modification of DNN architecture and the introduction of complex loss functions. This paper …

abstract abstraction applications art arxiv become box cs.cv detection distribution dynamic environment filtering inputs monitors networks neural networks object real-time safety safety-critical sota state type