ODExAI: A Comprehensive Object Detection Explainable AI Evaluation
Nguyen L, Nguyen HTT, Cao H (2026)
Publication Type: Conference contribution
Publication year: 2026
Journal
Publisher: Springer Science and Business Media Deutschland GmbH
Book Volume: 15956 LNAI
Pages Range: 118-133
Conference Proceedings Title: Lecture Notes in Computer Science
Event location: Potsdam
ISBN: 9783032028129
DOI: 10.1007/978-3-032-02813-6_9
Abstract
Explainable Artificial Intelligence (XAI) techniques for interpreting object detection models remain in an early stage, with no established standards for systematic evaluation. This absence of consensus hinders both the comparative analysis of methods and the informed selection of suitable approaches. To address this gap, we introduce the Object Detection Explainable AI Evaluation (ODExAI), a comprehensive framework designed to assess XAI methods in object detection based on three core dimensions: localization accuracy, faithfulness to model behavior, and computational complexity. We benchmark a set of XAI methods across two widely used object detectors (YOLOX and Faster R-CNN) and standard datasets (MS-COCO and PASCAL VOC). Empirical results demonstrate that region-based methods (e.g., D-CLOSE) achieve strong localization (PG = 88.49%) and high model faithfulness (OA = 0.863), though with substantial computational overhead (Time = 71.42 s). On the other hand, CAM-based methods (e.g., G-CAME) achieve superior localization (PG = 96.13%) and significantly lower runtime (Time = 0.54 s), but at the expense of reduced faithfulness (OA = 0.549). These findings demonstrate critical trade-offs among existing XAI approaches and reinforce the need for task-specific evaluation when deploying them in object detection pipelines. Our implementation and evaluation benchmarks are publicly available at: https://github.com/Analytics-Everywhere-Lab/odexai
Involved external institutions
Canada (CA)How to cite
APA:
Nguyen, L., Nguyen, H.T.T., & Cao, H. (2026). ODExAI: A Comprehensive Object Detection Explainable AI Evaluation. In Tanya Braun, Benjamin Paaßen, Frieder Stolzenburg (Eds.), Lecture Notes in Computer Science (pp. 118-133). Potsdam, DE: Springer Science and Business Media Deutschland GmbH.
MLA:
Nguyen, Loc, Hung Truong Thanh Nguyen, and Hung Cao. "ODExAI: A Comprehensive Object Detection Explainable AI Evaluation." Proceedings of the 48th German Conference on Artificial Intelligence, KI 2025, Potsdam Ed. Tanya Braun, Benjamin Paaßen, Frieder Stolzenburg, Springer Science and Business Media Deutschland GmbH, 2026. 118-133.
BibTeX: Download