{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T10:25:16Z","timestamp":1779099916741,"version":"3.51.4"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,10,6]],"date-time":"2021-10-06T00:00:00Z","timestamp":1633478400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,10,6]],"date-time":"2021-10-06T00:00:00Z","timestamp":1633478400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Discov Artif Intell"],"published-print":{"date-parts":[[2021,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>In this work we propose a workflow to deal with overlaid images\u2014images with superimposed text and company logos\u2014, which is very common in underwater monitoring videos and surveillance camera footage. It is demonstrated that it is possible to use Explaining Artificial Intelligence to improve deep learning models performance for image classification tasks in general. A deep learning model trained to classify metal surface defect, which previously had a low performance, is then evaluated with Layer-wise relevance propagation\u2014an Explaining Artificial Intelligence technique\u2014to identify problems in a dataset that hinder the training of deep learning models in a wide range of applications. Thereafter, it is possible to remove this unwanted information from the dataset\u2014using different approaches: from cutting part of the images to training a Generative Inpainting neural network model\u2014and retrain the model with the new preprocessed images. This proposed methodology improved F1 score in 20% when compared to the original trained dataset, validating the proposed workflow.<\/jats:p>","DOI":"10.1007\/s44163-021-00008-y","type":"journal-article","created":{"date-parts":[[2021,10,6]],"date-time":"2021-10-06T09:06:14Z","timestamp":1633511174000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":41,"title":["Improving deep learning performance by using Explainable Artificial Intelligence (XAI) approaches"],"prefix":"10.1007","volume":"1","author":[{"given":"Vitor","family":"Bento","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manoela","family":"Kohler","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pedro","family":"Diaz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leonardo","family":"Mendoza","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marco Aurelio","family":"Pacheco","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,10,6]]},"reference":[{"key":"8_CR1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90","author":"K He","year":"2016","unstructured":"He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit. 2016. https:\/\/doi.org\/10.1109\/CVPR.2016.90.","journal-title":"Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit"},{"key":"8_CR2","unstructured":"Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. In: 3rd international conference on learning representations ICLR 2015\u2014conference tracking proceedings. 2015. p. 1\u201314. https:\/\/arxiv.org\/abs\/1409.1556."},{"key":"8_CR3","doi-asserted-by":"publisher","first-page":"1291","DOI":"10.1002\/jcc.24764","volume":"38","author":"GB Goh","year":"2017","unstructured":"Goh GB, Hodas NO, Vishnu A. Deep learning for computational chemistry. J Comput Chem. 2017;38:1291\u2013307. https:\/\/doi.org\/10.1002\/jcc.24764.","journal-title":"J Comput Chem"},{"key":"8_CR4","doi-asserted-by":"publisher","unstructured":"Luckow A, Cook M, Ashcraft N, et al. Deep learning in the automotive industry: Applications and tools. In: Proceedings 2016 IEEE international conference big data, Big Data; 2016. p. 3759\u20133768. https:\/\/doi.org\/10.1109\/BigData.2016.7841045","DOI":"10.1109\/BigData.2016.7841045"},{"key":"8_CR5","unstructured":"Jin Y, Zhang J, Li M, et al (2017) Towards the automatic anime characters creation with generative adversarial networks. arXiv 92:1\u201316"},{"key":"8_CR6","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1109\/MM.2008.31","volume":"28","author":"E Lindholm","year":"2008","unstructured":"Lindholm E, Nickolls J, Oberman S, Montrym J. Nvidia Tesla: a unified graphics and computing architecture to enable flexible, programmable graphics and high-performance computing. IEEE Micro. 2008;28:39\u201355.","journal-title":"IEEE Micro"},{"key":"8_CR7","unstructured":"Doshi-Velez F, Kim B. Towards a rigorous science of interpretable machine learning. arXiv: 1702.08608 [Preprint].\u00a02017.\u00a0Available from: https:\/\/arxiv.org\/abs\/1702.08608"},{"key":"8_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1002\/widm.1312","volume":"9","author":"A Holzinger","year":"2019","unstructured":"Holzinger A, Langs G, Denk H, et al. Causability and explainability of artificial intelligence in medicine. Wiley Interdiscip Rev Data Min Knowl Discov. 2019;9:1\u201313. https:\/\/doi.org\/10.1002\/widm.1312.","journal-title":"Wiley Interdiscip Rev Data Min Knowl Discov"},{"key":"8_CR9","unstructured":"Samek W, Wiegand T, M\u00fcller KR. Explainable artificial intelligence: understanding, visualizing and interpreting deep learning models. arXiv: 1708.08296\u00a0[Preprint].\u00a02017. Available from: https:\/\/arxiv.org\/abs\/1708.08296"},{"key":"8_CR10","doi-asserted-by":"publisher","DOI":"10.1201\/9781420010749","author":"TF Gonzalez","year":"2007","unstructured":"Gonzalez TF. ImageNet classification with deep convolutional neural networks. Handb Approx Algorithms Metaheurifile. 2007. https:\/\/doi.org\/10.1201\/9781420010749.","journal-title":"Handb Approx Algorithms Metaheurifile"},{"key":"8_CR11","doi-asserted-by":"publisher","unstructured":"Balaban S, Labs L. Deep learning and face recognition: the state of the art. arXiv; 2019. p. 1\u20139. https:\/\/doi.org\/10.1117\/12.2181526","DOI":"10.1117\/12.2181526"},{"key":"8_CR12","doi-asserted-by":"publisher","unstructured":"Tian Y, Pei K, Jana S, Ray B. DeepTest: automated testing of deep-neural-network-driven autonomous cars. In: Proceedings of the 40th international conference on software engineering. 2018. p. 303\u2013314. https:\/\/doi.org\/10.1145\/3180155.3180220.","DOI":"10.1145\/3180155.3180220"},{"key":"8_CR13","doi-asserted-by":"publisher","first-page":"631","DOI":"10.1016\/j.procs.2020.01.057","volume":"165","author":"VN Dornadula","year":"2019","unstructured":"Dornadula VN, Geetha S. Credit card fraud detection using machine learning algorithms. Procedia Comput Sci. 2019;165:631\u201341. https:\/\/doi.org\/10.1016\/j.procs.2020.01.057.","journal-title":"Procedia Comput Sci"},{"key":"8_CR14","unstructured":"Wang D, Khosla A, Gargeya R, et al. Deep learning for identifying metastatic breast cancer. arXiv: 1606.05718\u00a0[Preprint]. 2016.\u00a0Available from: https:\/\/arxiv.org\/abs\/1606.05718"},{"key":"8_CR15","doi-asserted-by":"publisher","unstructured":"Lecture Notes in Artificial Intelligence. Explainable AI: interpreting, explaining and visualizing deep learning. In:\u00a0Samek W, Montavon G, Vedaldi A, Hansen LK, M\u00fcller KR,\u00a0editors.\u00a0Springer Nature.\u00a0https:\/\/doi.org\/10.1007\/978-3-030-28954-6.","DOI":"10.1007\/978-3-030-28954-6"},{"key":"8_CR16","doi-asserted-by":"publisher","first-page":"3818","DOI":"10.1093\/bioinformatics\/btaa203","volume":"36","author":"S Lee","year":"2020","unstructured":"Lee S, Lim S, Lee T, et al. Cancer subtype classification and modeling by pathway attention and propagation. Bioinformatics. 2020;36:3818\u201324. https:\/\/doi.org\/10.1093\/bioinformatics\/btaa203.","journal-title":"Bioinformatics"},{"key":"8_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0130140","volume":"10","author":"S Bach","year":"2015","unstructured":"Bach S, Binder A, Montavon G, et al. On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLoS ONE. 2015;10:1\u201346. https:\/\/doi.org\/10.1371\/journal.pone.0130140.","journal-title":"PLoS ONE"},{"key":"8_CR18","doi-asserted-by":"publisher","DOI":"10.3390\/s20061562","author":"X Lv","year":"2020","unstructured":"Lv X, Duan F, Jiang JJ, et al. Deep metallic surface defect detection: The new benchmark and detection network. Sensors (Switzerland). 2020. https:\/\/doi.org\/10.3390\/s20061562.","journal-title":"Sensors (Switzerland)"},{"key":"8_CR19","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917494","author":"F Kraus","year":"2019","unstructured":"Kraus F, Dietmayer K. Uncertainty estimation in one-stage object detection. 2019 IEEE Intell Transp Syst Conf ITSC. 2019. https:\/\/doi.org\/10.1109\/ITSC.2019.8917494.","journal-title":"2019 IEEE Intell Transp Syst Conf ITSC"},{"key":"8_CR20","doi-asserted-by":"publisher","unstructured":"Yu T, Li D, Yang Y, et al (2019) Robust person re-identification by modelling feature uncertainty. In: Proceedings of the IEEE international conference on computer vision 2019-October. p. 552\u201361. https:\/\/doi.org\/10.1109\/ICCV.2019.00064.","DOI":"10.1109\/ICCV.2019.00064"},{"key":"8_CR21","doi-asserted-by":"publisher","unstructured":"Chang J, Lan Z, Cheng C, Wei Y. Data uncertainty learning in face recognition. In: Proceedings of the IEEE computer society conference on computer vision pattern recognition; 2020. p. 5709\u201318. https:\/\/doi.org\/10.1109\/CVPR42600.2020.00575.","DOI":"10.1109\/CVPR42600.2020.00575"},{"key":"8_CR22","doi-asserted-by":"crossref","unstructured":"Smale S. On the mathematical foundations of electrical circuit theory. In: On the mathematical foundations of electrical circuit theory, vol 2. The Collected Papers of Stephen Smale; 2000. p. 951\u201368.","DOI":"10.1142\/9789812792822_0043"},{"key":"8_CR23","unstructured":"Gedraite ES, Hadad M. Investigation on the effect of a Gaussian Blur in image filtering and segmentation. Proceedings of the Elmar\u2014international symposium electron Mar; 2011. p. 393\u20136."},{"key":"8_CR24","doi-asserted-by":"publisher","unstructured":"Yu J, Lin Z, Yang J, et al. Generative image inpainting with contextual attention. In: Proceedings of the IEEE computer society conference computer vision Pattern Recognition; 2018. p. 5505\u201314. https:\/\/doi.org\/10.1109\/CVPR.2018.00577.","DOI":"10.1109\/CVPR.2018.00577"},{"key":"8_CR25","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1146\/annurev-statistics-010814-020120","volume":"2","author":"R Salakhutdinov","year":"2015","unstructured":"Salakhutdinov R. Learning deep generative models. Annu Rev Stat Its Appl. 2015;2:361\u201385. https:\/\/doi.org\/10.1146\/annurev-statistics-010814-020120.","journal-title":"Annu Rev Stat Its Appl"},{"key":"8_CR26","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow I, Pouget-Abadie J, Mirza M, et al. Generative adversarial networks. Commun ACM. 2020;63:139\u201344. https:\/\/doi.org\/10.1145\/3422622.","journal-title":"Commun ACM"},{"key":"8_CR27","doi-asserted-by":"publisher","unstructured":"Fuglede B, Topsoe F. Jensen-Shannon divergence and Hilbert space embedding BT\u2014IEEE international symposium on information theory; 2004. p. 31. https:\/\/doi.org\/10.1109\/ISIT.2004.1365067.","DOI":"10.1109\/ISIT.2004.1365067"},{"key":"8_CR28","unstructured":"Mirza M, Osindero S. Conditional generative adversarial nets. arXiv: 1411.1784\u00a0[Preprint]. 2014. Available from:\u00a0https:\/\/arxiv.org\/abs\/1411.1784"},{"key":"8_CR29","doi-asserted-by":"publisher","first-page":"503","DOI":"10.3169\/itej.71.503","volume":"71","author":"T Takahashi","year":"2017","unstructured":"Takahashi T. Image inpainting. Kyokai Joho Imeji Zasshi\/Journal Inst Image Inf Telev Eng. 2017;71:503\u20134. https:\/\/doi.org\/10.3169\/itej.71.503.","journal-title":"Kyokai Joho Imeji Zasshi\/Journal Inst Image Inf Telev Eng"},{"key":"8_CR30","unstructured":"Howard AG, Zhu M, Chen B, et al. MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv: 1704.04861\u00a0[Preprint].\u00a02017.  Available from:\u00a0https:\/\/arxiv.org\/abs\/1704.04861"},{"key":"8_CR31","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky O, Deng J, Su H, et al. ImageNet large scale visual recognition challenge. Int J Comput Vis. 2015;115:211\u201352. https:\/\/doi.org\/10.1007\/s11263-015-0816-y.","journal-title":"Int J Comput Vis"}],"container-title":["Discover Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44163-021-00008-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44163-021-00008-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44163-021-00008-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,6]],"date-time":"2021-10-06T09:39:07Z","timestamp":1633513147000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44163-021-00008-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,6]]},"references-count":31,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["8"],"URL":"https:\/\/doi.org\/10.1007\/s44163-021-00008-y","relation":{},"ISSN":["2731-0809"],"issn-type":[{"value":"2731-0809","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10,6]]},"assertion":[{"value":"5 April 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 August 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 October 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"There is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"9"}}