On the black-box explainability of object detection models for safe and trustworthy industrial applications

Vista sencilla de ítem
dc.contributor.authorAndrés Fernández, Alain
dc.contributor.authorMartínez Seras, Aitor
dc.contributor.authorLaña Aurrecoechea, Ibai
dc.contributor.authorSer Lorente, Javier del
dc.date.accessioned2025-02-25T10:15:49Z
dc.date.available2025-02-25T10:15:49Z
dc.date.issued2024-12
dc.date.updated2025-02-25T10:15:48Z
dc.description.abstractIn 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.en
dc.description.sponsorshipA. Andres, I. Laña and J. Del Ser receive support from the ULTIMATE project (ref. 101070162) funded by the European Commission under the HORIZON-CL4-DIS program (HORIZON-CL4-2021-HUMAN-01). J. Del Ser and I. Laña also acknowledge funding from the Basque Government (MATHMODE, IT1456-22)en
dc.identifier.citationAndres, A., Martinez-Seras, A., Laña, I., & Del Ser, J. (2024). On the black-box explainability of object detection models for safe and trustworthy industrial applications. Results in Engineering, 24. https://doi.org/10.1016/J.RINENG.2024.103498
dc.identifier.doi10.1016/J.RINENG.2024.103498
dc.identifier.eissn2590-1230
dc.identifier.urihttp://hdl.handle.net/20.500.14454/2368
dc.language.isoeng
dc.publisherElsevier B.V.
dc.rights© 2024 The Author(s)
dc.subject.otherExplainable Artificial Intelligence
dc.subject.otherIndustrial robotics
dc.subject.otherObject detection
dc.subject.otherSafe Artificial Intelligence
dc.subject.otherSingle-stage object detection
dc.subject.otherTrustworthy Artificial Intelligence
dc.titleOn the black-box explainability of object detection models for safe and trustworthy industrial applicationsen
dc.typejournal article
dcterms.accessRightsopen access
oaire.citation.titleResults in Engineering
oaire.citation.volume24
oaire.licenseConditionhttps://creativecommons.org/licenses/by-nc/4.0/
oaire.versionVoR
Archivos
Bloque original
Mostrando 1 - 1 de 1
Miniatura
Nombre:
andres_ontheblack_2024.pdf
Tamaño:
4.13 MB
Formato:
Adobe Portable Document Format
Descargar
Colecciones
Artículos