{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T20:31:14Z","timestamp":1773001874037,"version":"3.50.1"},"reference-count":29,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T00:00:00Z","timestamp":1758585600000},"content-version":"vor","delay-in-days":265,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Intelligent Systems"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:p>Lithium batteries are one class of key components in new\u2010energy vehicles, and surface defects are easily generated during production, causing serious threats to safety. Most deep learning methods of surface defect detection heavily rely on lots of high\u2010quality labeled samples. Unfortunately, it is very difficult and expensive to prepare defect datasets of lithium batteries in practice. To deal with this issue, this paper presents cross\u2010object transfer learning (COTL)\u2013based few\u2010shot surface defect detection of lithium batteries by resort to massive defect samples of other objects. The COTL model is composed of image preprocessing, feature extraction, feature fusion, and contrastive learning\u2010based defect detection modules. The ResNeXt\u2010101 network is used as the backbone to enhance feature extraction capability. The path aggregation feature pyramid network (PAFPN) is used to realize multiscale feature fusion. The contrastive learning branch is added to improve the discrimination ability among different categories of region proposals under few defect samples and increase the generalization ability. Then, experiments are done to testify the proposed method, where base\u2010class defect dataset from other objects and new\u2010class defect dataset from soft\u2010pack lithium batteries are adopted for training and testing. Furthermore, model comparison and ablation studies are performed. The results show that the recall rate, the AP50, the mAP, and the F1 values of the COTL model are much better than those of other existing models when only using few defect samples. In particular, when there are only 30 new\u2010class defect samples, the above four metrics of the COTL model are already larger than 0.90. The results testify that the proposed COTL model provides a more effective solution for few\u2010shot surface defect detection of lithium batteries.<\/jats:p>","DOI":"10.1155\/int\/4904188","type":"journal-article","created":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T06:25:03Z","timestamp":1758695103000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Cross\u2010Object Transfer Learning\u2010Based Few\u2010Shot Surface Defect Detection of Lithium Batteries"],"prefix":"10.1155","volume":"2025","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7354-0006","authenticated-orcid":false,"given":"Zhongsheng","family":"Chen","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0027-5456","authenticated-orcid":false,"given":"Bo","family":"Hu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1428-7677","authenticated-orcid":false,"given":"Wang","family":"Zuo","sequence":"additional","affiliation":[]}],"member":"311","published-online":{"date-parts":[[2025,9,23]]},"reference":[{"key":"e_1_2_11_1_2","doi-asserted-by":"crossref","unstructured":"RahimiA. Object Detection Using Deep Learning in a Manufacturing Plant to Improve Manual Inspection Proceedings of the 2021 IEEE International Conference on Prognostics and Health Management June 2021.","DOI":"10.1109\/ICPHM51084.2021.9486529"},{"key":"e_1_2_11_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jestch.2018.01.004"},{"key":"e_1_2_11_3_2","doi-asserted-by":"publisher","DOI":"10.3390\/ma14154175"},{"key":"e_1_2_11_4_2","doi-asserted-by":"crossref","unstructured":"MasciJ. MeierU. CiresanD. SchmidhuberJ. andFricoutG. Steel Defect Classification With Max-Pooling Convolutional Neural Networks Proceedings of International Joint Conference on Neural Networks (IJCNN) June 2012.","DOI":"10.1109\/IJCNN.2012.6252468"},{"key":"e_1_2_11_5_2","doi-asserted-by":"crossref","unstructured":"HuT. LuY. F. LiuC. andZhuangD. Y. Research on PCB Defect Detection Method Based on Deep Learning Proceedings of 5th International Conference on Computer Engineering and Intelligent Control (ICCEIC) October 2024.","DOI":"10.1109\/ICCEIC64099.2024.10775544"},{"key":"e_1_2_11_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/tie.2020.2982115"},{"key":"e_1_2_11_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/jsen.2022.3159293"},{"key":"e_1_2_11_8_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107717"},{"key":"e_1_2_11_9_2","doi-asserted-by":"publisher","DOI":"10.1093\/jcde\/qwac071"},{"key":"e_1_2_11_10_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10438-y"},{"key":"e_1_2_11_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.isatra.2024.09.018"},{"key":"e_1_2_11_12_2","doi-asserted-by":"publisher","DOI":"10.3390\/app13042402"},{"key":"e_1_2_11_13_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-022-02034-8"},{"key":"e_1_2_11_14_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107571"},{"key":"e_1_2_11_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2022.101566"},{"key":"e_1_2_11_16_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.05.021"},{"key":"e_1_2_11_17_2","doi-asserted-by":"publisher","DOI":"10.1142\/s0217979221400117"},{"key":"e_1_2_11_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/jsen.2022.3161331"},{"key":"e_1_2_11_19_2","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1884\/1\/012024"},{"key":"e_1_2_11_20_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-019-01476-x"},{"key":"e_1_2_11_21_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.apsusc.2013.09.002"},{"key":"e_1_2_11_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/access.2024.3402668"},{"key":"e_1_2_11_23_2","unstructured":"ChenZ. S. ZuoW. andHuB. Few-Shot Surface Defect Detection of Lithium Batteries Based on Deep Transfer Learning Proceedings of the International Conference on Equipment Intelligent Operation and Maintenance (ICEIOM2023) September 2023 21\u201323."},{"key":"e_1_2_11_24_2","doi-asserted-by":"crossref","unstructured":"XieS. N. GirshickR. DollarP. TuZ. W. andHeK. M. Aggregated Residual Transformations for Deep Neural Networks Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition April 2017.","DOI":"10.1109\/CVPR.2017.634"},{"key":"e_1_2_11_25_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.optlaseng.2020.106423"},{"key":"e_1_2_11_26_2","doi-asserted-by":"crossref","unstructured":"SzegedyC. VanhouckeV. IoffeS. andShlensJ. Rethinking the Inception Architecture for Computer Vision Proceedings of IEEE Conference on Computer Vision and Pattern Recognition June 2016.","DOI":"10.1109\/CVPR.2016.308"},{"key":"e_1_2_11_27_2","unstructured":"HeK. M. ZhangX. Y. RenS. Q. andSunJ. Deep Residual Learning for Image Recognition 2015."},{"key":"e_1_2_11_28_2","unstructured":"RenS. Q. HeK. M. GirshickR. andSunJ. Faster R-CNN: towards Real-Time Object Detection With Region Proposal Networks 2016."},{"key":"e_1_2_11_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00727"}],"container-title":["International Journal of Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/int\/4904188","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1155\/int\/4904188","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/int\/4904188","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T18:04:18Z","timestamp":1772993058000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/int\/4904188"}},"subtitle":[],"editor":[{"given":"Richard","family":"Murray","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":29,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10.1155\/int\/4904188"],"URL":"https:\/\/doi.org\/10.1155\/int\/4904188","archive":["Portico"],"relation":{},"ISSN":["0884-8173","1098-111X"],"issn-type":[{"value":"0884-8173","type":"print"},{"value":"1098-111X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]},"assertion":[{"value":"2025-05-26","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-04","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"4904188"}}