Visual attention-based siamese CNN with SoftmaxFocal loss for laser-induced damage change detection of optical elements
文献类型:期刊论文
作者 | Kou, Jingwei4,5; Zhan, Tao3; Zhou, Deyun5; Xie, Yu2; Da, Zhengshang4; Gong, Maoguo1 |
刊名 | NEUROCOMPUTING |
出版日期 | 2023-01-14 |
卷号 | 517 |
ISSN号 | 0925-2312;1872-8286 |
关键词 | Laser-induced damage Change detection Siamese convolutional neural network Visual attention mechanism SoftmaxFocal loss |
DOI | 10.1016/j.neucom.2022.10.074 |
产权排序 | 1 |
英文摘要 | With high-energy laser irradiating, the laser-induced damages may occur in the surfaces of optical ele-ments in laser facilities. As the laser-induced damage changes can badly affect regular and healthy oper-ation of laser facilities, it is essential to effectively detect real damage changes while suppressing meaningless and spurious changes in captured optical images. In order to achieve high-precision laser -induced damage change detection, this paper presents a novel deep learning model which exploits visual attention-based siamese convolutional neural network with SoftmaxFocal loss and significantly improves the performance of damage change detection. In the proposed model, an end-to-end classification net-work is designed and trained which fuses the spatial-channel domain collaborative attention modules into siamese convolutional neural network thus achieving more efficient feature extraction and represen-tation. For the purpose of addressing the unbalanced distribution of hard and easy samples, a novel loss function which is termed as SoftmaxFocal loss is put forward to train the proposed network. The SoftmaxFocal loss creatively introduces an additive focusing term into original softmax loss which greatly enhances the online hard sample mining ability of the proposed model. Experiments conducted on three real datasets demonstrate the validity and superiority of the proposed model.(c) 2022 Elsevier B.V. All rights reserved. |
语种 | 英语 |
出版者 | ELSEVIER |
WOS记录号 | WOS:000884436700014 |
源URL | [http://ir.opt.ac.cn/handle/181661/96247] |
专题 | 西安光学精密机械研究所_先进光学仪器研究室 |
通讯作者 | Zhou, Deyun |
作者单位 | 1.Xidian Univ, Key Lab Intelligent Percept & Image Understanding, Minist Educ, Xian 710071, Peoples R China 2.Shanxi Univ, Sch Comp & Informat Technol, Taiyuan 030006, Peoples R China 3.Northwest A&F Univ, Coll Informat Engn, Yangling 712100, Peoples R China 4.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Adv Opt Instrument Res Dept, Xian 710119, Peoples R China 5.Northwestern Polytech Univ, Sch Elect & Informat, Xian 710072, Peoples R China |
推荐引用方式 GB/T 7714 | Kou, Jingwei,Zhan, Tao,Zhou, Deyun,et al. Visual attention-based siamese CNN with SoftmaxFocal loss for laser-induced damage change detection of optical elements[J]. NEUROCOMPUTING,2023,517. |
APA | Kou, Jingwei,Zhan, Tao,Zhou, Deyun,Xie, Yu,Da, Zhengshang,&Gong, Maoguo.(2023).Visual attention-based siamese CNN with SoftmaxFocal loss for laser-induced damage change detection of optical elements.NEUROCOMPUTING,517. |
MLA | Kou, Jingwei,et al."Visual attention-based siamese CNN with SoftmaxFocal loss for laser-induced damage change detection of optical elements".NEUROCOMPUTING 517(2023). |
入库方式: OAI收割
来源:西安光学精密机械研究所
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。