On the Black-box Explainability of Object Detection Models for Safe and Trustworthy Industrial Applications

TL;DR

This paper introduces model-agnostic explainability methods for object detection models in industrial safety-critical applications, focusing on improving interpretability and evaluation metrics for real-world robotic scenarios.

Contribution

It proposes D-MFPP and D-Deletion, novel explainability techniques tailored for object detection, addressing limitations of existing methods and enhancing interpretability in high-risk environments.

Findings

D-Deletion effectively measures explanation faithfulness in scenes with multiple objects.

D-MFPP offers a viable alternative to D-RISE with fewer masks.

Methods are validated on real industrial and robotic datasets.

Abstract

In the realm of human-machine interaction, artificial intelligence has become a powerful tool for accelerating data modeling tasks. Object detection methods have achieved outstanding results and are widely used in critical domains like autonomous driving and video surveillance. However, their adoption in high-risk applications, where errors may cause severe consequences, remains limited. Explainable Artificial Intelligence methods aim to address this issue, but many existing techniques are model-specific and designed for classification tasks, making them less effective for object detection and difficult for non-specialists to interpret. In this work we focus on model-agnostic explainability methods for object detection models and propose D-MFPP, an extension of the Morphological Fragmental Perturbation Pyramid (MFPP) technique based on segmentation-based masks to generate explanations. Additionally, we introduce D-Deletion, a novel metric combining faithfulness and localization, adapted specifically to meet the unique demands of object detectors. We evaluate these methods on real-world industrial and robotic datasets, examining the influence of parameters such as the number of masks, model size, and image resolution on the quality of explanations. Our experiments use single-stage object detection models applied to two safety-critical robotic environments: i) a shared human-robot workspace where safety is of paramount importance, and ii) an assembly area of battery kits, where safety is critical due to the potential for damage among high-risk components. Our findings evince that D-Deletion effectively gauges the performance of explanations when multiple elements of the same class appear in a scene, while D-MFPP provides a promising alternative to D-RISE when fewer masks are used.