{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T14:18:15Z","timestamp":1760710695734,"version":"3.37.3"},"reference-count":62,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2021,8,30]],"date-time":"2021-08-30T00:00:00Z","timestamp":1630281600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,8,30]],"date-time":"2021-08-30T00:00:00Z","timestamp":1630281600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["51874022","51674031"],"award-info":[{"award-number":["51874022","51674031"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012165","name":"key technologies research and development program","doi-asserted-by":"publisher","award":["2018YFB0704304"],"award-info":[{"award-number":["2018YFB0704304"]}],"id":[{"id":"10.13039\/501100012165","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Mach. Learn. &amp; Cyber."],"published-print":{"date-parts":[[2022,2]]},"DOI":"10.1007\/s13042-021-01416-3","type":"journal-article","created":{"date-parts":[[2021,8,30]],"date-time":"2021-08-30T16:02:46Z","timestamp":1630339366000},"page":"431-445","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Generating robust real-time object detector with uncertainty via virtual adversarial training"],"prefix":"10.1007","volume":"13","author":[{"given":"Yipeng","family":"Chen","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1809-7413","authenticated-orcid":false,"given":"Ke","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Di","family":"He","sequence":"additional","affiliation":[]},{"given":"Xiaojuan","family":"Ban","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,8,30]]},"reference":[{"key":"1416_CR1","unstructured":"Kaiming H, Xiangyu Z, Shaoqing R, Jian Sun (2016) Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 770\u2013778"},{"key":"1416_CR2","unstructured":"Christian S et al (2015) Going deeper with convolutions. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 1\u20139"},{"key":"1416_CR3","unstructured":"Karen S and Andrew Z (2015) Very deep convolutional networks for large-scale image recognition. In: 3rd International Conference on Learning Representations (ICLR)"},{"key":"1416_CR4","unstructured":"Jie H, Li S, Gang S (2018) Squeeze-and-excitation networks. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 7132\u20137141"},{"key":"1416_CR5","unstructured":"Yunpeng C et al (2017) Dual path networks. In: Advances in Neural Information Processing Systems (NIPS), pp 4467\u20134475"},{"key":"1416_CR6","unstructured":"Saining X et al (2017) Aggregated residual transformations for deep neural networks. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 5987\u20135995"},{"issue":"2","key":"1416_CR7","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"E Mark","year":"2010","unstructured":"Mark E et al (2010) The pascal visual object classes (VOC) challenge. Int J Comput Vis 88(2):303\u2013338","journal-title":"Int J Comput Vis"},{"key":"1416_CR8","doi-asserted-by":"crossref","unstructured":"Tsung-Yi L et al (2014) Microsoft COCO: common objects in context. In: 2014 European Conference on Computer Vision (ECCV), pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1416_CR9","unstructured":"Joseph R, Ali F (2018) YOLOv3: an incremental improvement. CoRR. arXiv:1804.02767"},{"issue":"6","key":"1416_CR10","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"R Shaoqing","year":"2017","unstructured":"Shaoqing R, Kaiming H, Ross G, Jian S (2017) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137\u20131149","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1416_CR11","unstructured":"Ross G (2015) Fast R-CNN. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp 1440\u20131448"},{"key":"1416_CR12","first-page":"21","volume-title":"European conference on computer vision (ECCV)","author":"L Wei","year":"2016","unstructured":"Wei L et al (2016) SSD: single shot multibox detector. European conference on computer vision (ECCV). Springer, Cham, pp 21\u201337"},{"key":"1416_CR13","unstructured":"Shifeng Z, Longyin W, Xiao B, Zhen L, Stan L (2018) Single-shot refinement neural network for object detection. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), pp 4203\u20134212"},{"key":"1416_CR14","unstructured":"Peng Z, Bingbing N, Cong G, Jianguo H, Yi X (2018) Scale-transferrable object detection. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 528\u2013537"},{"key":"1416_CR15","doi-asserted-by":"crossref","unstructured":"Mark S, Andrew G.H, Menglong Z, Andrey Z, Liang-Chieh C (2018) MobileNetV2: inverted residuals and linear bottlenecks. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 4510\u20134520","DOI":"10.1109\/CVPR.2018.00474"},{"key":"1416_CR16","doi-asserted-by":"crossref","unstructured":"Ningning M, Xiangyu Z, Hai-Tao Z, Jian S (2018) ShuffleNet V2: practical guidelines for efficient cnn architecture design. In: 2018 European Conference on Computer Vision (ECCV), pp 122\u2013138","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"1416_CR17","unstructured":"Forrest NI (2016) SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size. CoRR. arXiv:1602.07360"},{"key":"1416_CR18","unstructured":"Fran\u00e7ois C (2017) Xception: deep learning with depthwise separable convolutions. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 1800\u20131807"},{"key":"1416_CR19","unstructured":"Alex K, Yarin G (2017) What uncertainties do we need in Bayesian deep learning for computer vision? In: The Advances in Neural Information Processing Systems(NIPS), pp 5574\u20135584"},{"key":"1416_CR20","unstructured":"Yarin G, Zoubin G (2016) Dropout as a Bayesian approximation: representing model uncertainty in deep learning. In: 2016 International Conference on Machine Learning (ICML), pp 1050\u20131059"},{"key":"1416_CR21","unstructured":"Sungjoon C, Kyungjae L, Sungbin L, Songhwai O (2018) Uncertainty-aware learning from demonstration using mixture density networks with sampling-free variance modeling. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp 6915\u20136922"},{"key":"1416_CR22","unstructured":"Yihui H, Chenchen Z, Jianren W, Marios S, Xiangyu Z (2019) Bounding box regression with uncertainty for accurate object detection. In: 2019 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 2888\u20132897"},{"key":"1416_CR23","unstructured":"Ian JG, Jonathon S, Christian S (2015) Explaining and harnessing adversarial examples. In: 2015 International Conference on Learning Representations (ICLR)"},{"key":"1416_CR24","unstructured":"Yinpeng D et al (2018) Boosting adversarial attacks with momentum. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 9185\u20139193"},{"key":"1416_CR25","unstructured":"Aleksander M et al (2018) Towards deep learning models resistant to adversarial attacks. In: 2018 International Conference on Learning Representations (ICLR)"},{"key":"1416_CR26","unstructured":"Florian T et al (2018) Ensemble adversarial training: attacks and defenses. In: 2018 International Conference on Learning Representations (ICLR)"},{"issue":"8","key":"1416_CR27","doi-asserted-by":"publisher","first-page":"1979","DOI":"10.1109\/TPAMI.2018.2858821","volume":"41","author":"M Takeru","year":"2019","unstructured":"Takeru M, Shin-ichi M, Masanori K, Shin I (2019) Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning. IEEE Trans Pattern Anal Mach Intell 41(8):1979\u20131993","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1416_CR28","unstructured":"Cihang X et al. (2017) adversarial examples for semantic segmentation and object detection. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp 1378\u20131387"},{"key":"1416_CR29","unstructured":"Xingxing W, Siyuan L, Ning C, Xiaochun C (2019) Transferable adversarial attacks for image and video object detection. In: Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI), pp 954\u2013960"},{"key":"1416_CR30","unstructured":"Ross BG, Jeff D, Trevor D, Jitendra M (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 580\u2013587"},{"key":"1416_CR31","unstructured":"Joseph R et al. (2016) You only look once: unified, real-time object detection. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 779\u2013788"},{"key":"1416_CR32","unstructured":"Tsung-Yi L et al (2017) Focal loss for dense object detection. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp 2999\u20133007"},{"key":"1416_CR33","unstructured":"Joseph R, Ali F (2017) YOLO9000: Better, Faster, Stronger. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 6517\u20136525."},{"key":"1416_CR34","unstructured":"Andrew GH et al (2017) MobileNets: efficient convolutional neural networks for mobile vision. CoRR. arXiv:1704.04861"},{"key":"1416_CR35","unstructured":"Xiangyu Z, Xinyu Z, Mengxiao L, Jian S (2018) ShuffleNet: an extremely efficient convolutional neural network for mobile devices. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 6848\u20136856"},{"key":"1416_CR36","unstructured":"Mingxing T et al (2019) EfficientNet: rethinking model scaling for convolutional neural networks. In: 2019 Proceedings of the 36th International Conference on Machine Learning (ICML), pp 6105\u20136114"},{"key":"1416_CR37","unstructured":"Rajat S et al (2020) ULSAM: ultra-lightweight subspace attention module for compact convolutional neural networks. In: IEEE Winter Conference on Applications of Computer Vision (WACV), pp 1616\u20131625"},{"key":"1416_CR38","unstructured":"Fahimeh F et al (2020) Lightweight residual densely connected convolutional neural network. CoRR. arXiv:2001.00526"},{"key":"1416_CR39","unstructured":"Xu M et al (2020) Cascaded context dependency: an extremely lightweight module for deep convolutional neural networks. In: 2020 IEEE International Conference on Image Processing (ICIP), pp 1741\u20131745"},{"key":"1416_CR40","unstructured":"Shyh J et al (2021) A novel lightweight convolutional neural network, exquisiteNetV2. CoRR. arXiv:2105.09008"},{"key":"1416_CR41","unstructured":"Charles B, Julien C, Koray K, Daan W (2015) Weight uncertainty in neural networks. CoRR. arXiv:1505.05424"},{"key":"1416_CR42","unstructured":"Balaji L, Alexander P, Charles B (2017) Simple and scalable predictive uncertainty estimation using deep ensembles. In: Advances in Neural Information Processing Systems (NIPS), pp 6402\u20136413"},{"key":"1416_CR43","unstructured":"Yarin G, Zoubin G (2016) Bayesian convolutional neural networks with bernoulli approximate variational inference. In: 2016 International Conference on Learning Representations (ICLR)"},{"key":"1416_CR44","unstructured":"Kumar S et al (2018) Uncertainty estimations by softplus normalization in bayesian convolutional neural networks with variational inference. CoRR. arXiv:1806.05978"},{"key":"1416_CR45","unstructured":"Lewis S, Yarin G (2018) Understanding measures of uncertainty for adversarial example detection. In: The Conference on Uncertainty in Artificial Intelligence (UAI), pp 560\u2013569"},{"key":"1416_CR46","unstructured":"Youngwan L et al (2020) Localization uncertainty estimation for anchor-free object detection. CoRR. arXiv:2006.15607"},{"key":"1416_CR47","unstructured":"Zhi T et al (2019) FCOS: fully convolutional one-stage object detection. In: 2019 IEEE International Conference on Computer Vision (ICCV), pp 9626\u20139635"},{"key":"1416_CR48","unstructured":"Yan L et al (2020) Loss rescaling by uncertainty inference for single-stage object detection. In: 2020 IEEE International Conference on Image Processing (ICIP), pp 698\u2013702"},{"key":"1416_CR49","unstructured":"Marius S et al (2020) MetaDetect: uncertainty quantification and prediction quality estimates for object detection. CoRR. arXiv:2010.01695"},{"key":"1416_CR50","unstructured":"Shixiang G, Luca R (2015) Towards deep neural network architectures robust to adversarial examples. In: the workshop at 2015 International Conference on Learning Representations (ICLR)."},{"key":"1416_CR51","unstructured":"Christian S et al (2014) Intriguing properties of neural networks. In: 2014 International Conference on Learning Representations (ICLR)."},{"key":"1416_CR52","first-page":"3365","volume":"27","author":"B Philip","year":"2014","unstructured":"Philip B, Ouais A, Doina P (2014) Learning with Pseudo-Ensembles. Adv Neural Inf Process Syst (NIPS) 27:3365\u20133373","journal-title":"Adv Neural Inf Process Syst (NIPS)"},{"key":"1416_CR53","unstructured":"Hongyi Z et al. (2018) mixup: beyond empirical risk minimization. In: 2018 International Conference on Learning Representations (ICLR)"},{"key":"1416_CR54","unstructured":"Sangdoo Y et al (2019) CutMix: regularization strategy to train strong classifiers with localizable features. In: 2019 IEEE International Conference on Computer Vision (ICCV), pp 6022\u20136031"},{"key":"1416_CR55","doi-asserted-by":"crossref","unstructured":"Yuxin W, Kaiming H (2018) Group normalization. In: 2016 European Conference on Computer Vision (ECCV), pp 3\u201319","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"1416_CR56","unstructured":"Sergey I, Christian S (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: 2015 International Conference on Machine Learning (ICML), pp 448\u2013456"},{"key":"1416_CR57","unstructured":"Hamid R et al (2019) Generalized intersection over union: a metric and a loss for bounding box regression. In: 2019 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 658\u2013666"},{"key":"1416_CR58","unstructured":"Navaneeth B, Bharat S, Rama C, Larry SD (2017) Improving object detection with one line of code. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp 5562\u20135570"},{"issue":"12","key":"1416_CR59","doi-asserted-by":"publisher","first-page":"3687","DOI":"10.1007\/s13042-019-00953-2","volume":"10","author":"H Xu","year":"2019","unstructured":"Xu H et al (2019) A Gaussian mixture model based combined resampling algorithm for classification of imbalanced credit data sets. Int J Mach Learn Cybern 10(12):3687\u20133699","journal-title":"Int J Mach Learn Cybern"},{"issue":"12","key":"1416_CR60","doi-asserted-by":"publisher","first-page":"3601","DOI":"10.1007\/s13042-019-00947-0","volume":"10","author":"A Habiba","year":"2019","unstructured":"Habiba A et al (2019) Multi-level features fusion and selection for human gait recognition: an optimized framework of Bayesian model and binomial distribution. Int J Mach Learn Cybern 10(12):3601\u20133618","journal-title":"Int J Mach Learn Cybern"},{"key":"1416_CR61","unstructured":"Diederik PK, Jimmy B (2015) Adam: a method for stochastic optimization. In: 2015 International Conference on Learning Representations (ICLR)."},{"key":"1416_CR62","unstructured":"Alexey B et al (2020) YOLOv4: optimal speed and accuracy of object detection. CoRR. arXiv:2004.10934"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-021-01416-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13042-021-01416-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-021-01416-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,21]],"date-time":"2022-01-21T09:37:28Z","timestamp":1642757848000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13042-021-01416-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,30]]},"references-count":62,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,2]]}},"alternative-id":["1416"],"URL":"https:\/\/doi.org\/10.1007\/s13042-021-01416-3","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"type":"print","value":"1868-8071"},{"type":"electronic","value":"1868-808X"}],"subject":[],"published":{"date-parts":[[2021,8,30]]},"assertion":[{"value":"6 June 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 August 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 August 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}