{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T17:32:09Z","timestamp":1770485529880,"version":"3.49.0"},"reference-count":27,"publisher":"World Scientific Pub Co Pte Ltd","issue":"15","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62006150"],"award-info":[{"award-number":["62006150"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012502","name":"Collaborative Innovation Center for Water Treatment Technology and Materials","doi-asserted-by":"crossref","award":["19YF1418400"],"award-info":[{"award-number":["19YF1418400"]}],"id":[{"id":"10.13039\/501100012502","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Shanghai Key Laboratory of Multidimensional Information Processing","award":["2020MIP001"],"award-info":[{"award-number":["2020MIP001"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J CIRCUIT SYST COMP"],"published-print":{"date-parts":[[2021,12,15]]},"abstract":"<jats:p> U-Net shows a remarkable performance and makes significant progress for segmentation task in medical images. Despite the outstanding achievements, the common case of defect detection in industrial scenes is still a challenging task, due to the noisy background, unpredictable environment, varying shapes and sizes of the defects. Traditional U-Net may not be suitable for low-quality images with low illumination and corruption, which are often presented in the practical collections in real-world scenes. In this paper, we propose an attention U-Net with feature fusion module for combining multi-scale features to detect the defects in noisy images automatically. Feature fusion module contains convolution kernels of different scales to capture shallow layer features and combine them with the high-dimensional features. Meanwhile, attention gates are used to enhance the robustness of skip connection between the feature maps. The proposed method is evaluated on two datasets. The best precision rate and MIoU of defect detection are 95.6% and 92.5%. The best F-score of concrete crack detection is 95.0%. Experimental results show that the proposed approach achieves promising results in both datasets. It demonstrates that our approach consistently outperforms other U-Net-based approaches for defect detection in low-quality images. Experimental results have shown the possibility of developing a mixture system that can be deployed in many applications, such as remote sensing image analysis, earthquake disaster situation assessment, and so on. <\/jats:p>","DOI":"10.1142\/s0218126621502728","type":"journal-article","created":{"date-parts":[[2021,5,25]],"date-time":"2021-05-25T08:23:48Z","timestamp":1621931028000},"source":"Crossref","is-referenced-by-count":12,"title":["Attention U-Net with Feature Fusion Module for Robust Defect Detection"],"prefix":"10.1142","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2769-022X","authenticated-orcid":false,"given":"Yu-Jie","family":"Xiong","sequence":"first","affiliation":[{"name":"School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, P. R. China"},{"name":"Shanghai Key Laboratory of Multidimensional Information Processing, East China Normal University, Shanghai 200241, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong-Bin","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yao","family":"Yao","sequence":"additional","affiliation":[{"name":"School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"219","published-online":{"date-parts":[[2021,5,25]]},"reference":[{"key":"S0218126621502728BIB001","doi-asserted-by":"publisher","DOI":"10.1016\/j.compstruc.2010.12.014"},{"key":"S0218126621502728BIB002","doi-asserted-by":"publisher","DOI":"10.1016\/j.protcy.2016.01.014"},{"key":"S0218126621502728BIB003","doi-asserted-by":"publisher","DOI":"10.1111\/mice.12141"},{"key":"S0218126621502728BIB004","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2009.2028250"},{"key":"S0218126621502728BIB005","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2017.2764844"},{"key":"S0218126621502728BIB006","doi-asserted-by":"publisher","DOI":"10.1111\/mice.12351"},{"key":"S0218126621502728BIB007","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2016.06.008"},{"key":"S0218126621502728BIB008","doi-asserted-by":"publisher","DOI":"10.1111\/mice.12263"},{"key":"S0218126621502728BIB009","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2572683"},{"key":"S0218126621502728BIB010","doi-asserted-by":"publisher","DOI":"10.1111\/mice.12412"},{"key":"S0218126621502728BIB011","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"S0218126621502728BIB012","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2019.04.025"},{"key":"S0218126621502728BIB013","doi-asserted-by":"publisher","DOI":"10.1080\/2150704X.2019.1574990"},{"key":"S0218126621502728BIB015","first-page":"271","volume-title":"Proc. Int. MICCAI Brainlesion Workshop","author":"Dolz J.","year":"2018"},{"key":"S0218126621502728BIB016","first-page":"237","volume-title":"Proc. Int. Conf. Telecommunications and Signal Processing","author":"Kolarik M.","year":"2019"},{"key":"S0218126621502728BIB017","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107404"},{"key":"S0218126621502728BIB018","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00223"},{"key":"S0218126621502728BIB019","doi-asserted-by":"publisher","DOI":"10.1109\/APCCAS.2018.8605652"},{"key":"S0218126621502728BIB020","first-page":"1","volume":"14","author":"Lian S.","year":"2015","journal-title":"IEEE Trans. Comput. Biol. Bioinform."},{"key":"S0218126621502728BIB021","first-page":"436","volume":"7","author":"Ding L.","year":"2019","journal-title":"IEEE Access"},{"key":"S0218126621502728BIB022","first-page":"547","volume":"7","author":"Song L.","year":"2019","journal-title":"IEEE Access"},{"key":"S0218126621502728BIB023","first-page":"1","volume-title":"Proc. Conf. Medical Imaging with Deep Learning","author":"Oktay O.","year":"2018"},{"key":"S0218126621502728BIB024","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-36711-4_13"},{"key":"S0218126621502728BIB025","first-page":"1","volume-title":"Proc. Int. Symp. Biomedical Imaging","author":"Abraham N.","year":"2019"},{"key":"S0218126621502728BIB026","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.11.002"},{"key":"S0218126621502728BIB027","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2019.04.005"},{"key":"S0218126621502728BIB028","first-page":"1","volume-title":"Proc. Int. Conf. Learning Representations","author":"Zhang H.","year":"2018"}],"container-title":["Journal of Circuits, Systems and Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S0218126621502728","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T08:51:36Z","timestamp":1643187096000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/abs\/10.1142\/S0218126621502728"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,25]]},"references-count":27,"journal-issue":{"issue":"15","published-print":{"date-parts":[[2021,12,15]]}},"alternative-id":["10.1142\/S0218126621502728"],"URL":"https:\/\/doi.org\/10.1142\/s0218126621502728","relation":{},"ISSN":["0218-1266","1793-6454"],"issn-type":[{"value":"0218-1266","type":"print"},{"value":"1793-6454","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,25]]},"article-number":"2150272"}}