{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T04:30:59Z","timestamp":1772166659967,"version":"3.50.1"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,8,8]],"date-time":"2020-08-08T00:00:00Z","timestamp":1596844800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2020,8,8]],"date-time":"2020-08-08T00:00:00Z","timestamp":1596844800000},"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":["J Big Data"],"published-print":{"date-parts":[[2020,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Transfer learning allows us to train deep architectures requiring a large number of learned parameters, even if the amount of available data is limited, by leveraging existing models previously trained for another task. In previous attempts to classify image-based software artifacts in the absence of big data, it was noted that standard off-the-shelf deep architectures such as VGG could not be utilized due to their large parameter space and therefore had to be replaced by customized architectures with fewer layers. This proves to be challenging to empirical software engineers who would like to make use of existing architectures without the need for customization.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Findings<\/jats:title>\n                    <jats:p>Here we explore the applicability of transfer learning utilizing models pre-trained on non-software engineering data applied to the problem of classifying software unified modeling language (UML) diagrams. Our experimental results show training reacts positively to transfer learning as related to sample size, even though the pre-trained model was not exposed to training instances from the software domain. We contrast the transferred network with other networks to show its advantage on different sized training sets, which indicates that transfer learning is equally effective to custom deep architectures in respect to classification accuracy when large amounts of training data is not available.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Our findings suggest that transfer learning, even when based on models that do not contain software engineering artifacts, can provide a pathway for using off-the-shelf deep architectures without customization. This provides an alternative to practitioners who want to apply deep learning to image-based classification but do not have the expertise or comfort to define their own network architectures.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s40537-020-00335-4","type":"journal-article","created":{"date-parts":[[2020,8,8]],"date-time":"2020-08-08T06:02:48Z","timestamp":1596866568000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":24,"title":["Exploring the efficacy of transfer learning in mining image-based software artifacts"],"prefix":"10.1186","volume":"7","author":[{"given":"Natalie","family":"Best","sequence":"first","affiliation":[]},{"given":"Jordan","family":"Ott","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0174-7002","authenticated-orcid":false,"given":"Erik J.","family":"Linstead","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,8,8]]},"reference":[{"key":"335_CR1","doi-asserted-by":"publisher","unstructured":"Ott J, Atchison A, Harnack P, Bergh A, Linstead E. A deep learning approach to identifying source code in images and video. 2018. p. 376\u201386. https:\/\/doi.org\/10.1145\/3196398.3196402.","DOI":"10.1145\/3196398.3196402"},{"issue":"3","key":"335_CR2","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, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M, et al. Imagenet large scale visual recognition challenge. Int J Comput Vis. 2015;115(3):211\u201352.","journal-title":"Int J Comput Vis"},{"issue":"1","key":"335_CR3","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1186\/s40537-019-0198-z","volume":"6","author":"J Ott","year":"2019","unstructured":"Ott J, Atchison A, Linstead EJ. Exploring the applicability of low-shot learning in mining software repositories. J Big Data. 2019;6(1):35. https:\/\/doi.org\/10.1186\/s40537-019-0198-z.","journal-title":"J Big Data"},{"key":"335_CR4","unstructured":"Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition; 2014. arXiv:1409.1556."},{"key":"335_CR5","unstructured":"Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. In: Proceedings of the 25th international conference on neural information processing systems - Volume 1. NIPS\u201912, pp. 1097\u20131105. USA: Curran Associates Inc.; 2012. http:\/\/dl.acm.org\/citation.cfm?id=2999134.2999257."},{"key":"335_CR6","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. 2015. CoRR arXiv:1512.03385.","DOI":"10.1109\/CVPR.2016.90"},{"key":"335_CR7","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A. Going deeper with convolutions. In: Computer vision and pattern recognition (CVPR). 2015. arXiv:1409.4842.","DOI":"10.1109\/CVPR.2015.7298594"},{"issue":"5","key":"335_CR8","doi-asserted-by":"publisher","first-page":"1285","DOI":"10.1109\/TMI.2016.2528162","volume":"35","author":"H Shin","year":"2016","unstructured":"Shin H, Roth HR, Gao M, Lu L, Xu Z, Nogues I, Yao J, Mollura D, Summers RM. Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Trans Med Imaging. 2016;35(5):1285\u201398. https:\/\/doi.org\/10.1109\/TMI.2016.2528162.","journal-title":"IEEE Trans Med Imaging"},{"key":"335_CR9","doi-asserted-by":"crossref","first-page":"532","DOI":"10.1007\/978-3-319-49409-8_46","volume-title":"Computer vision\u2014ECCV 2016 workshops","author":"N Bayramoglu","year":"2016","unstructured":"Bayramoglu N, Heikkil\u00e4 J. Transfer learning for cell nuclei classification in histopathology images. In: Hua G, J\u00e9gou H, editors. Computer vision\u2014ECCV 2016 workshops. Cham: Springer; 2016. p. 532\u20139."},{"key":"335_CR10","doi-asserted-by":"crossref","unstructured":"Ott J, Atchison A, Harnack P, Best N, Anderson H, Firmani C, Linstead E. Learning lexical features of programming languages from imagery using convolutional neural networks. In: Proceedings of the 26th conference on program comprehension. New York: ACM; 2018. p. 336\u20139.","DOI":"10.1145\/3196321.3196359"},{"key":"335_CR11","doi-asserted-by":"crossref","unstructured":"Alahmadi M, Hassel J, Parajuli B, Haiduc S, Kumar P. Accurately predicting the location of code fragments in programming video tutorials using deep learning. In: Proceedings of the 14th international conference on predictive models and data analytics in software engineering. New York: ACM; 2018. p. 2\u201311.","DOI":"10.1145\/3273934.3273935"},{"key":"335_CR12","doi-asserted-by":"publisher","unstructured":"Hebig R, Quang TH, Chaudron MRV, Robles G, Fernandez MA. The quest for open source projects that use uml: Mining github. In: Proceedings of the ACM\/IEEE 19th international conference on model driven engineering languages and systems. MODELS \u201916. New York: ACM; 2016. p. 173\u201383. https:\/\/doi.org\/10.1145\/2976767.2976778.","DOI":"10.1145\/2976767.2976778"},{"issue":"10","key":"335_CR13","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","volume":"22","author":"SJ Pan","year":"2010","unstructured":"Pan SJ, Yang Q. A survey on transfer learning. IEEE Trans Knowl Data Eng. 2010;22(10):1345\u201359. https:\/\/doi.org\/10.1109\/TKDE.2009.191.","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"335_CR14","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L. ImageNet: a large-scale hierarchical image database. In: CVPR09; 2009.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"335_CR15","volume-title":"Handbook of research on machine learning applications and trends: algorithms, methods and techniques\u20142 volumes","author":"ES Olivas","year":"2009","unstructured":"Olivas ES, Guerrero JDM, Sober MM, Benedito JRM, Lopez AJS. Handbook of research on machine learning applications and trends: algorithms, methods and techniques\u20142 volumes. Hershey: Information Science Reference - Imprint of: IGI Publishing; 2009."},{"key":"335_CR16","doi-asserted-by":"crossref","unstructured":"Bengio Y. Practical recommendations for gradient-based training of deep architectures. 2012. CoRR arXiv:1206.5533.","DOI":"10.1007\/978-3-642-35289-8_26"},{"key":"335_CR17","doi-asserted-by":"crossref","unstructured":"Zhou B, Khosla A, Lapedriza \u00c0, Oliva A, Torralba A. Learning deep features for discriminative localization. 2015. CoRR arXiv:1512.04150.","DOI":"10.1109\/CVPR.2016.319"},{"key":"335_CR18","unstructured":"Kotikalapudi R. contributors: keras-vis. GitHub; 2017."},{"key":"335_CR19","first-page":"399","volume":"1","author":"T Ho-Quang","year":"2014","unstructured":"Ho-Quang T, Chaudron MRV, Samuelsson I, Hjaltason J, Karasneh B, Osman H. Automatic classification of UML class diagrams from images. 2014 21st Asia-Pac Softw Eng Conf. 2014;1:399\u2013406.","journal-title":"2014 21st Asia-Pac Softw Eng Conf"},{"key":"335_CR20","unstructured":"Hjaltason J, Samuelsson I. Automatic classification of uml class diagrams through image feature extraction and machine learning. 2015."},{"key":"335_CR21","doi-asserted-by":"publisher","unstructured":"Moreno V, G\u00e9nova G, Alejandres M, Fraga A. Automatic classification of web images as UML diagrams. In: Proceedings of the 4th Spanish conference on information retrieval. CERI \u201916. New York: ACM; 2016. p. 17\u20131178. https:\/\/doi.org\/10.1145\/2934732.2934739.","DOI":"10.1145\/2934732.2934739"},{"key":"335_CR22","unstructured":"Krishna R, Menzies T. Bellwethers: a baseline method for transfer learning. 2017. arXiv e-prints. arXiv:1703\u201306218."},{"issue":"3","key":"335_CR23","doi-asserted-by":"publisher","first-page":"813","DOI":"10.1007\/s10664-014-9300-5","volume":"20","author":"E Kocaguneli","year":"2015","unstructured":"Kocaguneli E, Menzies T, Mendes E. Transfer learning in effort estimation. Empirical Softw Eng. 2015;20(3):813\u201343. https:\/\/doi.org\/10.1007\/s10664-014-9300-5.","journal-title":"Empirical Softw Eng"},{"issue":"3","key":"335_CR24","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1016\/j.infsof.2011.09.007","volume":"54","author":"Y Ma","year":"2012","unstructured":"Ma Y, Luo G, Zeng X, Chen A. Transfer learning for cross-company software defect prediction. Inf Softw Technol. 2012;54(3):248\u201356. https:\/\/doi.org\/10.1016\/j.infsof.2011.09.007.","journal-title":"Inf Softw Technol"},{"key":"335_CR25","doi-asserted-by":"publisher","unstructured":"Jing X, Wu F, Xiwei D, qi F, Xu B. Heterogeneous cross-company defect prediction by unified metric representation and CCA-based transfer learning. 2015. p. 496\u2013507. https:\/\/doi.org\/10.1145\/2786805.2786813.","DOI":"10.1145\/2786805.2786813"},{"key":"335_CR26","doi-asserted-by":"crossref","unstructured":"Jamshidi P, Velez M, K\u00e4stner C, Siegmund N, Kawthekar P. Transfer learning for improving model predictions in highly configurable software. 2017. CoRR arXiv:1704.00234.","DOI":"10.1109\/SEAMS.2017.11"},{"issue":"5","key":"335_CR27","doi-asserted-by":"publisher","first-page":"1299","DOI":"10.1109\/TMI.2016.2535302","volume":"35","author":"N Tajbakhsh","year":"2016","unstructured":"Tajbakhsh N, Shin J, Gurudu S, Hurst R, Kendall C, Gotway M, Liang J. Convolutional neural networks for medical image analysis: full training or fine tuning? IEEE Trans Med Imaging. 2016;35(5):1299\u2013312. https:\/\/doi.org\/10.1109\/TMI.2016.2535302.","journal-title":"IEEE Trans Med Imaging"}],"container-title":["Journal of Big Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-020-00335-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s40537-020-00335-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-020-00335-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,7]],"date-time":"2021-08-07T19:11:05Z","timestamp":1628363465000},"score":1,"resource":{"primary":{"URL":"https:\/\/journalofbigdata.springeropen.com\/articles\/10.1186\/s40537-020-00335-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8,8]]},"references-count":27,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,12]]}},"alternative-id":["335"],"URL":"https:\/\/doi.org\/10.1186\/s40537-020-00335-4","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-16922\/v1","asserted-by":"object"}]},"ISSN":["2196-1115"],"issn-type":[{"value":"2196-1115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,8,8]]},"assertion":[{"value":"7 March 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 July 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 August 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare that they have no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"59"}}