{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T20:10:22Z","timestamp":1773691822819,"version":"3.50.1"},"reference-count":28,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2024,1,14]],"date-time":"2024-01-14T00:00:00Z","timestamp":1705190400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Portuguese National Funds","award":["COMPETE2030"],"award-info":[{"award-number":["COMPETE2030"]}]},{"name":"Portuguese National Funds","award":["01\/RPA\/2022-C679908640-00009887"],"award-info":[{"award-number":["01\/RPA\/2022-C679908640-00009887"]}]},{"name":"Innovation and Digital Transition Program","award":["COMPETE2030"],"award-info":[{"award-number":["COMPETE2030"]}]},{"name":"Innovation and Digital Transition Program","award":["01\/RPA\/2022-C679908640-00009887"],"award-info":[{"award-number":["01\/RPA\/2022-C679908640-00009887"]}]},{"name":"ATLAS\u2014Trusted Autonomous Navigation","award":["COMPETE2030"],"award-info":[{"award-number":["COMPETE2030"]}]},{"name":"ATLAS\u2014Trusted Autonomous Navigation","award":["01\/RPA\/2022-C679908640-00009887"],"award-info":[{"award-number":["01\/RPA\/2022-C679908640-00009887"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Deep learning has rapidly increased in popularity, leading to the development of perception solutions for autonomous driving. The latter field leverages techniques developed for computer vision in other domains for accomplishing perception tasks such as object detection. However, the black-box nature of deep neural models and the complexity of the autonomous driving context motivates the study of explainability in these models that perform perception tasks. Moreover, this work explores explainable AI techniques for the object detection task in the context of autonomous driving. An extensive and detailed comparison is carried out between gradient-based and perturbation-based methods (e.g., D-RISE). Moreover, several experimental setups are used with different backbone architectures and different datasets to observe the influence of these aspects in the explanations. All the techniques explored consist of saliency methods, making their interpretation and evaluation primarily visual. Nevertheless, numerical assessment methods are also used. Overall, D-RISE and guided backpropagation obtain more localized explanations. However, D-RISE highlights more meaningful regions, providing more human-understandable explanations. To the best of our knowledge, this is the first approach to obtaining explanations focusing on the regression of the bounding box coordinates.<\/jats:p>","DOI":"10.3390\/s24020516","type":"journal-article","created":{"date-parts":[[2024,1,15]],"date-time":"2024-01-15T07:25:07Z","timestamp":1705303507000},"page":"516","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Explaining Bounding Boxes in Deep Object Detectors Using Post Hoc Methods for Autonomous Driving Systems"],"prefix":"10.3390","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7438-1793","authenticated-orcid":false,"given":"Caio","family":"Nogueira","sequence":"first","affiliation":[{"name":"Faculty of Engineering, University of Porto, 4200-465 Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8306-3362","authenticated-orcid":false,"given":"Lu\u00eds","family":"Fernandes","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, University of Porto, 4200-465 Porto, Portugal"},{"name":"Instituto de Engenharia de Sistemas e Computadores, Tecnologia e Ci\u00eancia, 4200-465 Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0590-4861","authenticated-orcid":false,"given":"Jo\u00e3o N. D.","family":"Fernandes","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, University of Porto, 4200-465 Porto, Portugal"},{"name":"Instituto de Engenharia de Sistemas e Computadores, Tecnologia e Ci\u00eancia, 4200-465 Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3760-2473","authenticated-orcid":false,"given":"Jaime S.","family":"Cardoso","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, University of Porto, 4200-465 Porto, Portugal"},{"name":"Instituto de Engenharia de Sistemas e Computadores, Tecnologia e Ci\u00eancia, 4200-465 Porto, Portugal"}]}],"member":"1968","published-online":{"date-parts":[[2024,1,14]]},"reference":[{"key":"ref_1","unstructured":"Ren, S., He, K., Girshick, R.B., and Sun, J. (2015). Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. arXiv."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Redmon, J., and Farhadi, A. (2016). YOLO9000: Better, Faster, Stronger. arXiv.","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Ilkov\u00e1, V., and Ilka, A. (2017, January 6\u20139). Legal aspects of autonomous vehicles\u2014An overview. Proceedings of the 2017 21st International Conference on Process Control (PC), Strbske Pleso, Slovakia.","DOI":"10.1109\/PC.2017.7976252"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Ramon, Y., Farrokhnia, R., Matz, S.C., and Martens, D. (2021). Explainable AI for Psychological Profiling from Behavioral Data: An Application to Big Five Personality Predictions from Financial Transaction Records. Information, 12.","DOI":"10.3390\/info12120518"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Renda, A., Ducange, P., Marcelloni, F., Sabella, D., Filippou, M.C., Nardini, G., Stea, G., Virdis, A., Micheli, D., and Rapone, D. (2022). Federated Learning of Explainable AI Models in 6G Systems: Towards Secure and Automated Vehicle Networking. Information, 13.","DOI":"10.3390\/info13080395"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1230","DOI":"10.23919\/cje.2022.00.093","article-title":"Towards V2I Age-Aware Fairness Access: A DQN Based Intelligent Vehicular Node Training and Test Method","volume":"32","author":"Qiong","year":"2023","journal-title":"Chin. J. Electron."},{"key":"ref_7","unstructured":"Atakishiyev, S., Salameh, M., Yao, H., and Goebel, R. (2021). Explainable Artificial Intelligence for Autonomous Driving: A Comprehensive Overview and Field Guide for Future Research Directions. arXiv."},{"key":"ref_8","unstructured":"Chen, C., Li, O., Tao, C., Barnett, A.J., Su, J., and Rudin, C. (2019). This Looks Like That: Deep Learning for Interpretable Image Recognition. arXiv."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Donnelly, J., Barnett, A.J., and Chen, C. (2022). Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypes. arXiv.","DOI":"10.1109\/CVPR52688.2022.01002"},{"key":"ref_10","unstructured":"Xue, M., Huang, Q., Zhang, H., Cheng, L., Song, J., Wu, M., and Song, M. (2022). ProtoPFormer: Concentrating on Prototypical Parts in Vision Transformers for Interpretable Image Recognition. arXiv."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"41482","DOI":"10.1109\/ACCESS.2021.3064838","article-title":"These do not Look Like Those: An Interpretable Deep Learning Model for Image Recognition","volume":"9","author":"Singh","year":"2021","journal-title":"IEEE Access"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Zeiler, M.D., and Fergus, R. (2013). Visualizing and Understanding Convolutional Networks. arXiv.","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref_13","unstructured":"Sundararajan, M., Taly, A., and Yan, Q. (2017). Axiomatic Attribution for Deep Networks. arXiv."},{"key":"ref_14","unstructured":"Das, A., and Rad, P. (2020). Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Survey. arXiv."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Das, A., Vedantam, R., Cogswell, M., Parikh, D., and Batra, D. (2016). Grad-CAM: Why did you say that? Visual Explanations from Deep Networks via Gradient-based Localization. arXiv.","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref_16","unstructured":"Springenberg, J.T., Dosovitskiy, A., Brox, T., and Riedmiller, M. (2015). Striving for Simplicity: The All Convolutional Net. arXiv."},{"key":"ref_17","unstructured":"Smilkov, D., Thorat, N., Kim, B., Vi\u00e9gas, F.B., and Wattenberg, M. (2017). SmoothGrad: Removing noise by adding noise. arXiv."},{"key":"ref_18","unstructured":"Petsiuk, V., Das, A., and Saenko, K. (2018). RISE: Randomized Input Sampling for Explanation of Black-box Models. arXiv."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Petsiuk, V., Jain, R., Manjunatha, V., Morariu, V.I., Mehra, A., Ordonez, V., and Saenko, K. (2020). Black-box Explanation of Object Detectors via Saliency Maps. arXiv.","DOI":"10.1109\/CVPR46437.2021.01128"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., and Guestrin, C. (2016). \u201cWhy Should I Trust You?\u201d: Explaining the Predictions of Any Classifier. arXiv.","DOI":"10.1145\/2939672.2939778"},{"key":"ref_21","unstructured":"Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., and Garnett, R. (2017). Advances in Neural Information Processing Systems, Curran Associates, Inc."},{"key":"ref_22","first-page":"841","article-title":"Counterfactual Explanations Without Opening the Black Box: Automated Decisions and the GDPR","volume":"31","author":"Wachter","year":"2017","journal-title":"Harv. J. Law Technol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1231","DOI":"10.1177\/0278364913491297","article-title":"Vision meets Robotics: The KITTI Dataset","volume":"32","author":"Geiger","year":"2013","journal-title":"Int. J. Robot. Res. (IJRR)"},{"key":"ref_24","unstructured":"Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., and Zisserman, A. (2023, April 01). The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results. Available online: http:\/\/www.pascal-network.org\/challenges\/VOC\/voc2012\/workshop\/index.html."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2015). Deep Residual Learning for Image Recognition. arXiv.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Prabhushankar, M., Kwon, G., Temel, D., and AlRegib, G. (2020, January 25\u201328). Contrastive Explanations In Neural Networks. Proceedings of the 2020 IEEE International Conference on Image Processing (ICIP), Abu Dhabi, United Arab Emirates.","DOI":"10.1109\/ICIP40778.2020.9190927"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Lin, T., Maire, M., Belongie, S.J., Bourdev, L.D., Girshick, R.B., Hays, J., Perona, P., Ramanan, D., Doll\u2019a r, P., and Zitnick, C.L. (2014). Microsoft COCO: Common Objects in Context. arXiv.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1084","DOI":"10.1007\/s11263-017-1059-x","article-title":"Top-Down Neural Attention by Excitation Backprop","volume":"126","author":"Zhang","year":"2018","journal-title":"Int. J. Comput. Vis."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/2\/516\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T13:46:28Z","timestamp":1760103988000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/2\/516"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,14]]},"references-count":28,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2024,1]]}},"alternative-id":["s24020516"],"URL":"https:\/\/doi.org\/10.3390\/s24020516","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,14]]}}}