{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T00:00:47Z","timestamp":1769644847895,"version":"3.49.0"},"reference-count":44,"publisher":"Association for Computing Machinery (ACM)","issue":"2","funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["62034007"],"award-info":[{"award-number":["62034007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Des. Autom. Electron. Syst."],"published-print":{"date-parts":[[2026,3,31]]},"abstract":"<jats:p>Accurate analysis of nanoscale defects in semiconductor manufacturing is essential for optimizing yield and reliability. Existing methods heavily rely on large, labor-intensive datasets and primarily focus on macroscopic defect distributions rather than finer nanoscale defect morphology. In this study, we introduce a novel hybrid weakly supervised segmentation framework for scanning electron microscope (SEM) images, which significantly reduces labeling demands while maintaining high precision. Our approach consists of two interconnected subnetworks: the first is dedicated to precise defect localization and image cropping, and the second performs detailed segmentation of the localized regions. Additionally, we propose an enhanced H-WSSNet that employs Leaky ReLU and a novel multi-level feature fusion mechanism, addressing gradient vanishing during training and improving the model\u2019s adaptive feature fusion and selection capabilities. Extensive validation on a dataset of 1,328 real-world SEM images shows that our model achieves accuracy comparable to fully supervised methods, but with only 10% of the labeling workload. This advancement opens up new possibilities for efficient and scalable high-precision defect segmentation in semiconductor manufacturing.<\/jats:p>","DOI":"10.1145\/3780101","type":"journal-article","created":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T10:56:24Z","timestamp":1765536984000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A Hybrid Weakly Supervised Approach for enhanced High-Precision SEM Defect Segmentation in Nanoscale Semiconductor Manufacturing"],"prefix":"10.1145","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-6179-829X","authenticated-orcid":false,"given":"Yibo","family":"Qiao","sequence":"first","affiliation":[{"name":"Zhejiang University","place":["Hangzhou, China"]},{"name":"Zhejiang ICsprout Semiconductor Co., Ltd.","place":["Hangzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8541-0499","authenticated-orcid":false,"given":"Weiping","family":"Xie","sequence":"additional","affiliation":[{"name":"Zhejiang University","place":["Hangzhou, China"]},{"name":"Zhejiang ICsprout Semiconductor Co., Ltd.","place":["Hangzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0437-2861","authenticated-orcid":false,"given":"Shunyuan","family":"Lou","sequence":"additional","affiliation":[{"name":"Zhejiang University","place":["Hangzhou, China"]},{"name":"Zhejiang ICsprout Semiconductor Co., Ltd.","place":["Hangzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4414-232X","authenticated-orcid":false,"given":"Qian","family":"Jin","sequence":"additional","affiliation":[{"name":"Zhejiang University","place":["Hangzhou, China"]},{"name":"Zhejiang ICsprout Semiconductor Co., Ltd.","place":["Hangzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6614-0049","authenticated-orcid":false,"given":"Lichao","family":"Zeng","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China","place":["Hefei, China"]},{"name":"Zhejiang ICsprout Semiconductor Co., Ltd.","place":["Hefei, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9302-6696","authenticated-orcid":false,"given":"Yining","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University","place":["Hangzhou, China"]},{"name":"Zhejiang ICsprout Semiconductor Co., Ltd.","place":["Hangzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5153-6698","authenticated-orcid":false,"given":"Qi","family":"Sun","sequence":"additional","affiliation":[{"name":"Zhejiang University","place":["Hangzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2610-7522","authenticated-orcid":false,"given":"Cheng","family":"Zhuo","sequence":"additional","affiliation":[{"name":"Zhejiang University","place":["Hangzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,1,28]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"crossref","unstructured":"Vijay Badrinarayanan et\u00a0al. 2017. Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Transactions on Pattern Analysis And Machine Intelligence 39 12 (2017) 2481\u20132495.","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"e_1_3_1_3_2","doi-asserted-by":"crossref","DOI":"10.1142\/S2424905X18400020","article-title":"Towards a computed-aided diagnosis system in colonoscopy: Automatic polyp segmentation using convolution neural networks","author":"Brandao Patrick","year":"2018","unstructured":"Patrick Brandao et\u00a0al. 2018. Towards a computed-aided diagnosis system in colonoscopy: Automatic polyp segmentation using convolution neural networks. Journal of Medical Robotics Research 3, 2 (2018), 1840002.","journal-title":"Journal of Medical Robotics Research"},{"key":"e_1_3_1_4_2","first-page":"205","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Cao Hu","year":"2022","unstructured":"Hu Cao, Yueyue Wang, Joy Chen, Dongsheng Jiang, Xiaopeng Zhang, Qi Tian, and Manning Wang. 2022. Swin-unet: Unet-like pure transformer for medical image segmentation. In Proceedings of the European Conference on Computer Vision. Springer, 205\u2013218."},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00901"},{"key":"e_1_3_1_6_2","volume-title":"Proceedings of the IEEE International Symposium on Semiconductor Manufacturing Conference Proceedings.","author":"Chen FL","year":"2003","unstructured":"FL Chen et\u00a0al. 2003. Logic product yield analysis by wafer bin map pattern recognition supervised neural network. In Proceedings of the IEEE International Symposium on Semiconductor Manufacturing Conference Proceedings."},{"key":"e_1_3_1_7_2","doi-asserted-by":"crossref","unstructured":"Liang-Chieh Chen et\u00a0al. 2018. Encoder-decoder with atrous separable convolution for semantic image segmentation. In Proceedings of the European Conference on Computer Vision (ECCV). 801\u2013818.","DOI":"10.1007\/978-3-030-01234-2_49"},{"issue":"2","key":"e_1_3_1_8_2","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1080\/10170660209509189","article-title":"Developing a data mining method for wafer binmap clustering and an empirical study in a semiconductor manufacturing fab","volume":"19","author":"Chien Chen-Fu","year":"2002","unstructured":"Chen-Fu Chien, Ting-Hao Lin, Qiao-Wen Liu, Cheng-Yung Peng, Shao-Chung Hsu, and Chia-Chi Huang. 2002. Developing a data mining method for wafer binmap clustering and an empirical study in a semiconductor manufacturing fab. Journal of the Chinese Institute of Industrial Engineers 19, 2 (2002), 23\u201338.","journal-title":"Journal of the Chinese Institute of Industrial Engineers"},{"key":"e_1_3_1_9_2","article-title":"Semi-supervised learning with context-conditional generative adversarial networks","author":"Denton Emily","year":"2016","unstructured":"Emily Denton et\u00a0al. 2016. Semi-supervised learning with context-conditional generative adversarial networks. arXiv:1611.06430. Retrieved from https:\/\/arxiv.org\/abs\/1611.06430 (2016).","journal-title":"a"},{"key":"e_1_3_1_10_2","doi-asserted-by":"crossref","first-page":"2584","DOI":"10.1109\/IJCNN.2016.7727522","volume-title":"Proceedings of the 2016 International Joint Conference on Neural Networks (IJCNN)","author":"Faghih-Roohi Shahrzad","year":"2016","unstructured":"Shahrzad Faghih-Roohi, Siamak Hajizadeh, Alfredo N\u00fa\u00f1ez, Robert Babuska, and Bart De Schutter. 2016. Deep convolutional neural networks for detection of rail surface defects. In Proceedings of the 2016 International Joint Conference on Neural Networks (IJCNN). IEEE, 2584\u20132589."},{"key":"e_1_3_1_11_2","doi-asserted-by":"crossref","unstructured":"Shu-Kai S Fan et\u00a0al. 2019. Key parameter identification and defective wafer detection of semiconductor manufacturing processes using image processing techniques. IEEE Transactions on Semiconductor Manufacturing 32 4 (2019) 544\u2013552.","DOI":"10.1109\/TSM.2019.2929765"},{"key":"e_1_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Xinyu Fu et\u00a0al. 2021. Region-guided pixel-level label generation for weakly supervised semantic segmentation. In Proceedings of The 4th International Conference on Control and Computer Vision 1 6 (2021).","DOI":"10.1145\/3484274.3484275"},{"key":"e_1_3_1_13_2","doi-asserted-by":"crossref","unstructured":"Hao Geng et\u00a0al. 2023. Mixed-type wafer failure pattern recognition. In Proceedings of The 28th Asia and South Pacific Design Automation Conference. 727\u2013732.","DOI":"10.1145\/3566097.3568363"},{"key":"e_1_3_1_14_2","article-title":"Depth estimation from a single SEM image using pixel-wise fine-tuning with multimodal data","author":"Houben Tim","year":"2022","unstructured":"Tim Houben et\u00a0al. 2022. Depth estimation from a single SEM image using pixel-wise fine-tuning with multimodal data. Machine Vision and Applications 33, 4, (2022) 56.","journal-title":"Machine Vision and Applications"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_3_1_16_2","volume-title":"Proceedings of the MATEC Web of Conferences","author":"Huang Chung-Chi","year":"2018","unstructured":"Chung-Chi Huang et\u00a0al. 2018. Study on machine learning based intelligent defect detection system. In Proceedings of the MATEC Web of Conferences"},{"key":"e_1_3_1_17_2","article-title":"Few-shot semantic segmentation for consumer electronics: An inter-class relation mining approach","author":"Huang Huafei","year":"2024","unstructured":"Huafei Huang, Xu Yuan, Shuo Yu, Wenhong Zhao, Osama Alfarraj, Amr Tolba, and Feng Xia. 2024. Few-shot semantic segmentation for consumer electronics: An inter-class relation mining approach. IEEE Transactions on Consumer Electronics 70, 1 (2024), 3709\u20133721.","journal-title":"IEEE Transactions on Consumer Electronics"},{"key":"e_1_3_1_18_2","first-page":"692","volume-title":"Proceedings of the International Conference on Medical Image Computing and Computer-assisted Intervention","author":"Ibtehaz Nabil","year":"2023","unstructured":"Nabil Ibtehaz and Daisuke Kihara. 2023. Acc-unet: A completely convolutional unet model for the 2020s. In Proceedings of the International Conference on Medical Image Computing and Computer-assisted Intervention. Springer, 692\u2013702."},{"key":"e_1_3_1_19_2","first-page":"1280","volume-title":"Proceedings of the 2016 21st International Conference on Methods and Models in Automation and Robotics (MMAR)","author":"Laucka Andrius","year":"2016","unstructured":"Andrius Laucka, Darius Andriukaitis, Algimantas Valinevicius, and Dangirutis Navikas. 2016. Computer vision system for defects detection in PET preform. In Proceedings of the 2016 21st International Conference on Methods and Models in Automation and Robotics (MMAR). IEEE, 1280\u20131285."},{"key":"e_1_3_1_20_2","article-title":"Automated semiconductor defect inspection in scanning electron microscope images: A systematic review","author":"Lechien Thibault","year":"2023","unstructured":"Thibault Lechien et\u00a0al. 2023. Automated semiconductor defect inspection in scanning electron microscope images: A systematic review. arXiv:2308.08376. Retrieved from https:\/\/arxiv.org\/abs\/2308.08376 (2023).","journal-title":"a"},{"key":"e_1_3_1_21_2","first-page":"3","volume-title":"Proceedings of the icml","volume":"30","author":"Maas Andrew L","year":"2013","unstructured":"Andrew L Maas, Awni Y Hannun, Andrew Y Ng, et\u00a0al. 2013. Rectifier nonlinearities improve neural network acoustic models. In Proceedings of the icml, Vol. 30. Atlanta, GA, 3."},{"key":"e_1_3_1_22_2","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1109\/ASMC.2000.902551","volume-title":"Proceedings of the 2000 IEEE\/SEMI Advanced Semiconductor Manufacturing Conference and Workshop. ASMC 2000 (Cat. No. 00CH37072)","author":"Malinaric Dan","year":"2000","unstructured":"Dan Malinaric et\u00a0al. 2000. Case study for root cause analysis of yield problems. In Proceedings of the 2000 IEEE\/SEMI Advanced Semiconductor Manufacturing Conference and Workshop. ASMC 2000 (Cat. No. 00CH37072). IEEE, 8\u201313."},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSM.2018.2795466"},{"key":"e_1_3_1_24_2","doi-asserted-by":"crossref","unstructured":"Shuanlong Niu et\u00a0al. 2019. DefectGAN: Weakly-supervised defect detection using generative adversarial network. IEEE 15th International Conference on Automation Science And Engineering (CASE). IEEE 127\u2013132.","DOI":"10.1109\/COASE.2019.8843204"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2016.2522191"},{"key":"e_1_3_1_26_2","doi-asserted-by":"crossref","unstructured":"Deepak Pathak et\u00a0al. 2015. Constrained convolutional neural networks for weakly supervised segmentation. In Proceedings of the IEEE International Conference on Computer Vision. 1796\u20131804.","DOI":"10.1109\/ICCV.2015.209"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3655939"},{"key":"e_1_3_1_28_2","volume-title":"Semiconductor Manufacturing Technology","author":"Quirk Michael","year":"2001","unstructured":"Michael Quirk et\u00a0al. 2001. Semiconductor Manufacturing Technology. Vol. 1. Prentice Hall Upper Saddle River, NJ."},{"issue":"3","key":"e_1_3_1_29_2","first-page":"929","article-title":"A generic deep-learning-based approach for automated surface inspection","volume":"48","author":"Ren Ruoxu","year":"2017","unstructured":"Ruoxu Ren, Terence Hung, and Kay Chen Tan. 2017. A generic deep-learning-based approach for automated surface inspection. IEEE Transactions on Cybernetics 48, 3 (2017), 929\u2013940.","journal-title":"IEEE Transactions on Cybernetics"},{"key":"e_1_3_1_30_2","doi-asserted-by":"crossref","unstructured":"Olaf Ronneberger et\u00a0al. 2015. U-net: Convolutional networks for biomedical image segmentation. International Conference on Medical Image Computing And Computer-Assisted Intervention. Cham: Springer international publishing (2015) 234\u2013241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"issue":"3","key":"e_1_3_1_31_2","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1016\/j.mser.2010.06.007","article-title":"Trends in semiconductor defect engineering at the nanoscale","volume":"70","author":"Seebauer Edmund G","year":"2010","unstructured":"Edmund G Seebauer et\u00a0al. 2010. Trends in semiconductor defect engineering at the nanoscale. Materials Science and Engineering: R: Reports 70, 3-6 (2010), 151\u2013168.","journal-title":"Materials Science and Engineering: R: Reports"},{"key":"e_1_3_1_32_2","doi-asserted-by":"crossref","unstructured":"Ramprasaath R Selvaraju et\u00a0al. 2017. Grad-cam: Visual explanations from deep networks via gradient-based localization. In Proceedings of The IEEE International Conference on Computer Vision. 618\u2013626.","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_1_33_2","doi-asserted-by":"crossref","unstructured":"Wei Shen et\u00a0al. 2023. A survey on label-efficient deep image segmentation: Bridging the gap between weak supervision and dense prediction. IEEE Transactions on Pattern Analysis And Machine Intelligence 45 8 (2023) 9284\u20139305.","DOI":"10.1109\/TPAMI.2023.3246102"},{"key":"e_1_3_1_34_2","article-title":"CS-WSCDNet: Class activation mapping and segment anything model-based framework for weakly supervised change detection","author":"Wang Lukang","year":"2023","unstructured":"Lukang Wang, Min Zhang, and Wenzhong Shi. 2023. CS-WSCDNet: Class activation mapping and segment anything model-based framework for weakly supervised change detection. IEEE Transactions on Geoscience and Remote Sensing 61 (2023) 1\u201312.","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"e_1_3_1_35_2","doi-asserted-by":"crossref","unstructured":"Qijing Wang et\u00a0al. 2022. WaferHSL: Wafer failure pattern classification with efficient human-like staged learning. In Proceedings of The 41st IEEE\/ACM International Conference on Computer-Aided Design. 1\u20138.","DOI":"10.1145\/3508352.3549466"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cirp.2016.04.072"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2015.2417676"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3237896"},{"key":"e_1_3_1_40_2","article-title":"Empirical evaluation of rectified activations in convolutional network","author":"Xu Bing","year":"2015","unstructured":"Bing Xu, Naiyan Wang, Tianqi Chen, and Mu Li. 2015. Empirical evaluation of rectified activations in convolutional network. arXiv:1505.00853. Retrieved from https:\/\/arxiv.org\/abs\/1505.00853","journal-title":"a"},{"key":"e_1_3_1_41_2","article-title":"Stacked convolutional sparse denoising auto-encoder for identification of defect patterns in semiconductor wafer map","author":"Yu Jianbo","year":"2019","unstructured":"Jianbo Yu et\u00a0al. 2019. Stacked convolutional sparse denoising auto-encoder for identification of defect patterns in semiconductor wafer map. Computers in Industry 109 (2019), 121\u2013133.","journal-title":"Computers in Industry"},{"issue":"9","key":"e_1_3_1_42_2","first-page":"5866","article-title":"Weakly supervised object localization and detection: A survey","volume":"44","author":"Zhang Dingwen","year":"2021","unstructured":"Dingwen Zhang, Junwei Han, Gong Cheng, and Ming-Hsuan Yang. 2021. Weakly supervised object localization and detection: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 9 (2021), 5866\u20135885.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_1_43_2","doi-asserted-by":"crossref","first-page":"2066","DOI":"10.1109\/IGARSS47720.2021.9553768","volume-title":"Proceedings of the 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS","author":"Zheng Zhuo","year":"2021","unstructured":"Zhuo Zheng, Yinhe Liu, Shiqi Tian, Junjue Wang, Ailong Ma, and Yanfei Zhong. 2021. Weakly supervised semantic change detection via label refinement framework. In Proceedings of the 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS. IEEE, 2066\u20132069."},{"key":"e_1_3_1_44_2","doi-asserted-by":"crossref","unstructured":"Bolei Zhou et\u00a0al. 2016. Learning deep features for discriminative localization. In Proceedings of The IEEE Conference on Computer Vision And Pattern Recognition. 2921\u20132929.","DOI":"10.1109\/CVPR.2016.319"},{"key":"e_1_3_1_45_2","first-page":"10","volume-title":"Proceedings of the 2023 IEEE 9th Intl Conference on Big Data Security on Cloud (BigDataSecurity), IEEE Intl Conference on High Performance and Smart Computing,(HPSC) and IEEE Intl Conference on Intelligent Data and Security (IDS)","author":"Zhu Kaiyin","year":"2023","unstructured":"Kaiyin Zhu, Neal N Xiong, and Mingming Lu. 2023. A survey of weakly-supervised semantic segmentation. In Proceedings of the 2023 IEEE 9th Intl Conference on Big Data Security on Cloud (BigDataSecurity), IEEE Intl Conference on High Performance and Smart Computing,(HPSC) and IEEE Intl Conference on Intelligent Data and Security (IDS). IEEE, 10\u201315."}],"container-title":["ACM Transactions on Design Automation of Electronic Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3780101","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T11:49:38Z","timestamp":1769600978000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3780101"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,28]]},"references-count":44,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,3,31]]}},"alternative-id":["10.1145\/3780101"],"URL":"https:\/\/doi.org\/10.1145\/3780101","relation":{},"ISSN":["1084-4309","1557-7309"],"issn-type":[{"value":"1084-4309","type":"print"},{"value":"1557-7309","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,28]]},"assertion":[{"value":"2025-07-07","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-25","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}