{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T10:27:52Z","timestamp":1772792872607,"version":"3.50.1"},"reference-count":17,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia","award":["PNURSP2025R500"],"award-info":[{"award-number":["PNURSP2025R500"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>In recent years, object detection has become an indispensable component in various critical applications, ranging from autonomous driving to surveillance systems. However, achieving high detection accuracy alone is insufficient; models must also be transparent and interpretable to foster trust and ensure reliable decision-making, especially in safety-critical domains. Traditional supervised approaches require large amounts of labeled data, which is often expensive and time-consuming to obtain. Additionally, these models typically function as \u201cblack boxes,\u201d providing limited insight into their decision processes. This article introduces SemiXAI-Net, a semi-supervised learning framework optimized for object detection tasks while incorporating explainable AI (XAI) techniques to enhance transparency. By utilizing a teacher-student architecture, the framework iteratively refines pseudo-labels, effectively improving both model performance and interpretability. The experimental evaluation was performed using the Common Objects in Context (COCO) dataset (a real-world benchmark) alongside synthetic datasets to simulate semi-supervised conditions. A labeled subset of COCO images was combined with unlabeled data (both from COCO\u2019s unannotated images and synthetic sources) for training. The framework was implemented on NVIDIA Tesla V100 GPUs using PyTorch, with hyperparameters optimized for stability (batch size: 32, learning rate: 0.001) and efficiency. To enable real-time interpretability, the student model integrated Gradient-weighted Class Activation Mapping (Grad-CAM) and Local Interpretable Model-Agnostic Explanations (LIME) techniques, generating visual explanations during inference. Training spanned 10 epochs with early stopping to mitigate overfitting risks. SemiXAI-Net achieves a superior accuracy of 93%, precision of 94%, recall of 95%, and an F1-score of 94.5%. In comparison, traditional methods reach a maximum accuracy of 87%. The explainability score of SemiXAI-Net stands at 94%, significantly surpassing the traditional method\u2019s score of 71%. Additionally, the framework demonstrates a generalization ability of 94% on unseen data, making it highly adaptable to new environments. These results highlight SemiXAI-Net\u2019s potential for real-world applications, particularly in critical domains like autonomous driving, where both high performance and model transparency are essential.<\/jats:p>","DOI":"10.7717\/peerj-cs.3523","type":"journal-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T08:04:07Z","timestamp":1772784247000},"page":"e3523","source":"Crossref","is-referenced-by-count":0,"title":["SemiXAI-Net: XAI-driven semi-supervised object detection\n                    <i>via<\/i>\n                    iterative pseudo-label refinement and spatiotemporal consistency"],"prefix":"10.7717","volume":"12","author":[{"given":"Hassam","family":"Tahir","sequence":"first","affiliation":[{"name":"School of Computing, Engineering and Mathematics, Western Sydney University, Sydney, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9968-8439","authenticated-orcid":true,"given":"Walaa","family":"Alayed","sequence":"additional","affiliation":[{"name":"Department of Information Technology, Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4929-3316","authenticated-orcid":true,"given":"Waqar Ul","family":"Hassan","sequence":"additional","affiliation":[{"name":"Department of Mathematics, Government College University Lahore, Lahore, Pakistan"}]},{"given":"Truong X.","family":"Tran","sequence":"additional","affiliation":[{"name":"School of Science, Engineering and Technology, Penn State Harrisburg, The Pennsylvania State University, PA, United States"}]}],"member":"4443","published-online":{"date-parts":[[2026,3,6]]},"reference":[{"issue":"3","key":"10.7717\/peerj-cs.3523\/ref-1","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.inffus.2019.12.012","article-title":"Explainable artificial intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI","volume":"58","author":"Arrieta","year":"2020","journal-title":"Information Fusion"},{"key":"10.7717\/peerj-cs.3523\/ref-2","doi-asserted-by":"publisher","first-page":"4307","DOI":"10.1007\/s00500-019-04195-w","article-title":"Improving predictive uncertainty estimation using Dropout\u2013Hamiltonian Monte Carlo","volume":"24","author":"Hern\u00e1ndez","year":"2020","journal-title":"Soft Computing"},{"issue":"2","key":"10.7717\/peerj-cs.3523\/ref-3","doi-asserted-by":"publisher","first-page":"100520","DOI":"10.1016\/j.vehcom.2022.100520","article-title":"Detecting in-vehicle intrusion via semi-supervised learning-based convolutional adversarial autoencoders","volume":"38","author":"Hoang","year":"2022","journal-title":"Vehicular Communications"},{"key":"10.7717\/peerj-cs.3523\/ref-4","first-page":"817","article-title":"Object detection from video tubelets with convolutional neural networks","author":"Kang","year":"2016"},{"issue":"2","key":"10.7717\/peerj-cs.3523\/ref-5","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1109\/jas.2020.1003021","article-title":"Artificial intelligence applications in the development of autonomous vehicles: a survey","volume":"7","author":"Ma","year":"2020","journal-title":"IEEE\/CAA Journal of Automatica Sinica"},{"key":"10.7717\/peerj-cs.3523\/ref-6","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2408.04482","article-title":"SegXAL: Explainable active learning for semantic segmentation in driving scene scenarios","author":"Mandalika","year":"2024"},{"key":"10.7717\/peerj-cs.3523\/ref-7","first-page":"487","article-title":"Interpretable deep learning: evaluating yolo models and xai techniques for video annotation","volume":"2023","author":"Mokdad","year":"2023"},{"issue":"8","key":"10.7717\/peerj-cs.3523\/ref-8","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1016\/j.patrec.2024.08.008","article-title":"Saliency-based video summarization for face anti-spoofing","volume":"185","author":"Muhammad","year":"2024","journal-title":"Pattern Recognition Letters"},{"issue":"10","key":"10.7717\/peerj-cs.3523\/ref-9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3657647","article-title":"A survey on the applications of semi-supervised learning to cyber-security","volume":"56","author":"Mvula","year":"2024","journal-title":"ACM Computing Surveys"},{"issue":"12","key":"10.7717\/peerj-cs.3523\/ref-10","doi-asserted-by":"publisher","first-page":"4928","DOI":"10.1109\/tits.2019.2949915","article-title":"A systematic literature review about the impact of artificial intelligence on autonomous vehicle safety","volume":"21","author":"Nascimento","year":"2019","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"10.7717\/peerj-cs.3523\/ref-11","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2006.05278","article-title":"An overview of deep semi-supervised learning","author":"Ouali","year":"2020"},{"key":"10.7717\/peerj-cs.3523\/ref-12","first-page":"509","article-title":"Semi-supervised learning with a teacher-student network for generalized attribute prediction","author":"Shin","year":"2020"},{"key":"10.7717\/peerj-cs.3523\/ref-13","doi-asserted-by":"publisher","first-page":"6452","DOI":"10.1109\/tip.2020.2989100","article-title":"Learning from synthetic images via active pseudo-labeling","volume":"29","author":"Song","year":"2020","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.7717\/peerj-cs.3523\/ref-14","doi-asserted-by":"publisher","first-page":"109107","DOI":"10.1016\/j.compeleceng.2024.109107","article-title":"A hybrid evolutionary weighted ensemble of deep transfer learning models for retinal vessel segmentation and diabetic retinopathy detection","volume":"115","author":"Vij","year":"2024","journal-title":"Computers and Electrical Engineering"},{"key":"10.7717\/peerj-cs.3523\/ref-15","article-title":"Class-distribution-aware pseudo-labeling for semi-supervised multi-label learning","volume":"36","author":"Xie","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.7717\/peerj-cs.3523\/ref-16","first-page":"3060","article-title":"End-to-end semi-supervised object detection with soft teacher","author":"Xu","year":"2021"},{"issue":"1","key":"10.7717\/peerj-cs.3523\/ref-17","doi-asserted-by":"publisher","first-page":"1063","DOI":"10.1609\/aaai.v27i1.8642","article-title":"Video saliency detection via dynamic consistent spatio-temporal attention modelling","volume":"27","author":"Zhong","year":"2013","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-3523.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3523.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3523.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3523.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T08:04:11Z","timestamp":1772784251000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-3523"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":17,"alternative-id":["10.7717\/peerj-cs.3523"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.3523","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,6]]},"article-number":"e3523"}}