{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T16:49:19Z","timestamp":1780591759454,"version":"3.54.1"},"reference-count":41,"publisher":"MDPI AG","issue":"14","license":[{"start":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T00:00:00Z","timestamp":1658188800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"BMBF","award":["Cosemio FKZ 03F0812C"],"award-info":[{"award-number":["Cosemio FKZ 03F0812C"]}]},{"name":"BMBF","award":["Isymoo FKZ 0324254D"],"award-info":[{"award-number":["Isymoo FKZ 0324254D"]}]},{"name":"BMWi","award":["Cosemio FKZ 03F0812C"],"award-info":[{"award-number":["Cosemio FKZ 03F0812C"]}]},{"name":"BMWi","award":["Isymoo FKZ 0324254D"],"award-info":[{"award-number":["Isymoo FKZ 0324254D"]}]},{"name":"German Research Foundation (DFG)","award":["Cosemio FKZ 03F0812C"],"award-info":[{"award-number":["Cosemio FKZ 03F0812C"]}]},{"name":"German Research Foundation (DFG)","award":["Isymoo FKZ 0324254D"],"award-info":[{"award-number":["Isymoo FKZ 0324254D"]}]},{"name":"Open Access Publication Fund of Bielefeld University","award":["Cosemio FKZ 03F0812C"],"award-info":[{"award-number":["Cosemio FKZ 03F0812C"]}]},{"name":"Open Access Publication Fund of Bielefeld University","award":["Isymoo FKZ 0324254D"],"award-info":[{"award-number":["Isymoo FKZ 0324254D"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Data augmentation is an established technique in computer vision to foster the generalization of training and to deal with low data volume. Most data augmentation and computer vision research are focused on everyday images such as traffic data. The application of computer vision techniques in domains like marine sciences has shown to be not that straightforward in the past due to special characteristics, such as very low data volume and class imbalance, because of costly manual annotation by human domain experts, and general low species abundances. However, the data volume acquired today with moving platforms to collect large image collections from remote marine habitats, like the deep benthos, for marine biodiversity assessment and monitoring makes the use of computer vision automatic detection and classification inevitable. In this work, we investigate the effect of data augmentation in the context of taxonomic classification in underwater, i.e., benthic images. First, we show that established data augmentation methods (i.e., geometric and photometric transformations) perform differently in marine image collections compared to established image collections like the Cityscapes dataset, showing everyday traffic images. Some of the methods even decrease the learning performance when applied to marine image collections. Second, we propose new data augmentation combination policies motivated by our observations and compare their effect to those proposed by the AutoAugment algorithm and can show that the proposed augmentation policy outperforms the AutoAugment results for marine image collections. We conclude that in the case of small marine image datasets, background knowledge, and heuristics should sometimes be applied to design an effective data augmentation method.<\/jats:p>","DOI":"10.3390\/s22145383","type":"journal-article","created":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T23:10:22Z","timestamp":1658272222000},"page":"5383","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["The Impact of Data Augmentations on Deep Learning-Based Marine Object Classification in Benthic Image Transects"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5997-9087","authenticated-orcid":false,"given":"Mingkun","family":"Tan","sequence":"first","affiliation":[{"name":"Biodata Mining Group, Bielefeld University, P.O. Box 100131, 33501 Bielefeld, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1857-5040","authenticated-orcid":false,"given":"Daniel","family":"Langenk\u00e4mper","sequence":"additional","affiliation":[{"name":"Biodata Mining Group, Bielefeld University, P.O. Box 100131, 33501 Bielefeld, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7986-1158","authenticated-orcid":false,"given":"Tim W.","family":"Nattkemper","sequence":"additional","affiliation":[{"name":"Biodata Mining Group, Bielefeld University, P.O. Box 100131, 33501 Bielefeld, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,7,19]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1016\/j.margeo.2014.03.012","article-title":"Autonomous Underwater Vehicles (AUVs): Their past, present and future contributions to the advancement of marine geoscience","volume":"352","author":"Wynn","year":"2014","journal-title":"Mar. Geol."},{"key":"ref_2","unstructured":"Christ, R.D., and Wernli, R.L. (2013). The ROV Manual: A User Guide for Remotely Operated Vehicles, Butterworth-Heinemann."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Langenk\u00e4mper, D., Kevelaer, R.V., and Nattkemper, T.W. (2018). Strategies for tackling the class imbalance problem in marine image classification. International Conference on Pattern Recognition, Springer.","DOI":"10.1007\/978-3-030-05792-3_3"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Wei, Y., Yu, X., Hu, Y., and Li, D. (2012, January 16\u201318). Development a zooplankton recognition method for dark field image. Proceedings of the 2012 5th International Congress on Image and Signal Processing, Chongqing, China.","DOI":"10.1109\/CISP.2012.6469941"},{"key":"ref_5","unstructured":"Bewley, M., Douillard, B., Nourani-Vatani, N., Friedman, A., Pizarro, O., and Williams, S. (2012, January 3\u20135). Automated species detection: An experimental approach to kelp detection from sea-floor AUV images. Proceedings of the Australasian Conference on Robotics and Automation, Wellingto, New Zealand."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"21847","DOI":"10.1007\/s11042-017-4585-1","article-title":"FDCNet: Filtering deep convolutional network for marine organism classification","volume":"77","author":"Lu","year":"2018","journal-title":"Multimed. Tools Appl."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1016\/j.compeleceng.2016.08.008","article-title":"Underwater image de-scattering and classification by deep neural network","volume":"54","author":"Li","year":"2016","journal-title":"Comput. Electr. Eng."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Liu, X., Jia, Z., Hou, X., Fu, M., Ma, L., and Sun, Q. (2019, January 17\u201320). Real-time marine animal images classification by embedded system based on mobilenet and transfer learning. Proceedings of the OCEANS 2019-Marseille, Marseille, France.","DOI":"10.1109\/OCEANSE.2019.8867190"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Langenk\u00e4mper, D., Simon-Lled\u00f3, E., Hosking, B., Jones, D.O., and Nattkemper, T.W. (2019). On the impact of Citizen Science-derived data quality on deep learning based classification in marine images. PLoS ONE, 14.","DOI":"10.1371\/journal.pone.0218086"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"506","DOI":"10.3389\/fmars.2020.00506","article-title":"Gear-induced concept drift in marine images and its effect on deep learning classification","volume":"7","author":"Purser","year":"2020","journal-title":"Front. Mar. Sci."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Irfan, M., Zheng, J., Iqbal, M., and Arif, M.H. (2020). A novel feature extraction model to enhance underwater image classification. International Symposium on Intelligent Computing Systems, Springer.","DOI":"10.1007\/978-3-030-43364-2_8"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1109\/JOE.2017.2786878","article-title":"Deep image representations for coral image classification","volume":"44","author":"Mahmood","year":"2018","journal-title":"IEEE J. Ocean. Eng."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"3937580","DOI":"10.1155\/2020\/3937580","article-title":"Marine organism detection and classification from underwater vision based on the deep CNN method","volume":"2020","author":"Han","year":"2020","journal-title":"Math. Probl. Eng."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"372","DOI":"10.1016\/j.neucom.2019.01.084","article-title":"Faster R-CNN for marine organisms detection and recognition using data augmentation","volume":"337","author":"Huang","year":"2019","journal-title":"Neurocomputing"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Xu, L., Bennamoun, M., An, S., Sohel, F., and Boussaid, F. (2019). Deep learning for marine species recognition. Handbook of Deep Learning Applications, Springer.","DOI":"10.1007\/978-3-030-11479-4_7"},{"key":"ref_16","unstructured":"Zhuang, P., Xing, L., Liu, Y., Guo, S., and Qiao, Y. (2017). Marine Animal Detection and Recognition with Advanced Deep Learning Models. CLEF (Working Notes), Springer."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Xu, Y., Zhang, Y., Wang, H., and Liu, X. (2017, January 22\u201325). Underwater image classification using deep convolutional neural networks and data augmentation. Proceedings of the 2017 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC), Xiamen, China.","DOI":"10.1109\/ICSPCC.2017.8242527"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"104458","DOI":"10.1016\/j.conengprac.2020.104458","article-title":"Review on deep learning techniques for marine object recognition: Architectures and algorithms","volume":"118","author":"Wang","year":"2020","journal-title":"Control. Eng. Pract."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"NgoGia, T., Li, Y., Jin, D., Guo, J., Li, J., and Tang, Q. (2021). Real-Time Sea Cucumber Detection Based on YOLOv4-Tiny and Transfer Learning Using Data Augmentation. International Conference on Swarm Intelligence, Springer.","DOI":"10.1007\/978-3-030-78811-7_12"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Xie, C., Tan, M., Gong, B., Wang, J., Yuille, A.L., and Le, Q.V. (2020, January 14\u201319). Adversarial examples improve image recognition. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Virtual.","DOI":"10.1109\/CVPR42600.2020.00090"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"9176","DOI":"10.1109\/JSTARS.2021.3109600","article-title":"Progressive data augmentation method for remote sensing ship image classification based on imaging simulation system and neural style transfer","volume":"14","author":"Xiao","year":"2021","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Chu, P., Bian, X., Liu, S., and Ling, H. (2020). Feature space augmentation for long-tailed data. European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-030-58526-6_41"},{"key":"ref_23","unstructured":"DeVries, T., and Taylor, G.W. (2017). Dataset augmentation in feature space. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Li, C., Huang, Z., Xu, J., and Yan, Y. (2019, January 11\u201313). Data Augmentation using Conditional Generative Adversarial Network for Underwater Target Recognition. Proceedings of the 2019 IEEE International Conference on Signal, Information and Data Processing (ICSIDP), Chongqing, China.","DOI":"10.1109\/ICSIDP47821.2019.9173174"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Antoniou, A., Storkey, A., and Edwards, H. (2018). Augmenting image classifiers using data augmentation generative adversarial networks. International Conference on Artificial Neural Networks, Springer.","DOI":"10.1007\/978-3-030-01424-7_58"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Mane, D., Vasudevan, V., and Le, Q.V. (2019, January 16\u201320). Autoaugment: Learning augmentation strategies from data. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00020"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"5858","DOI":"10.1109\/ACCESS.2017.2696121","article-title":"Smart augmentation learning an optimal data augmentation strategy","volume":"5","author":"Lemley","year":"2017","journal-title":"IEEE Access"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Dabouei, A., Soleymani, S., Taherkhani, F., and Nasrabadi, N.M. (2021, January 19\u201325). Supermix: Supervising the mixing data augmentation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Virtual.","DOI":"10.1109\/CVPR46437.2021.01358"},{"key":"ref_29","unstructured":"Naveed, H. (2021). Survey: Image mixing and deleting for data augmentation. arXiv."},{"key":"ref_30","unstructured":"Kang, G., Dong, X., Zheng, L., and Yang, Y. (2017). Patchshuffle regularization. arXiv."},{"key":"ref_31","unstructured":"O\u2019Gara, S., and McGuinness, K. (2019). Comparing Data Augmentation Strategies for Deep Image Classification, Technological University Dublin."},{"key":"ref_32","unstructured":"Engstrom, L., Tran, B., Tsipras, D., Schmidt, L., and Madry, A. (2018). A Rotation and a Translation Suffice: Fooling Cnns with Simple Transformations. arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1186\/s40537-019-0197-0","article-title":"A survey on image data augmentation for deep learning","volume":"6","author":"Shorten","year":"2019","journal-title":"J. Big Data"},{"key":"ref_34","first-page":"6665","article-title":"Fast autoaugment","volume":"32","author":"Lim","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Shijie, J., Ping, W., Peiyi, J., and Siping, H. (2017, January 20\u201322). Research on data augmentation for image classification based on convolution neural networks. Proceedings of the 2017 Chinese Automation Congress (CAC), Jinan, China.","DOI":"10.1109\/CAC.2017.8243510"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"102395","DOI":"10.1016\/j.pocean.2020.102395","article-title":"Subtle variation in abyssal terrain induces significant change in benthic megafaunal abundance, diversity, and community structure","volume":"186","author":"Durden","year":"2020","journal-title":"Prog. Oceanogr."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"102508","DOI":"10.1016\/j.pocean.2020.102508","article-title":"Enduring science: Three decades of observing the Northeast Atlantic from the Porcupine Abyssal Plain Sustained Observatory (PAP-SO)","volume":"191","author":"Hartman","year":"2021","journal-title":"Prog. Oceanogr."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"795","DOI":"10.4319\/lom.2014.12.795","article-title":"A new method for ecological surveying of the abyss using autonomous underwater vehicle photography","volume":"12","author":"Morris","year":"2014","journal-title":"Limnol. Oceanogr. Methods"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/j.pocean.2018.11.003","article-title":"Megafaunal variation in the abyssal landscape of the Clarion Clipperton Zone","volume":"170","author":"Bett","year":"2019","journal-title":"Prog. Oceanogr."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., and Schiele, B. The Cityscapes Dataset for Semantic Urban Scene Understanding. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Recognition (CVPR), Las Vegas, NV, USA, 27\u201330 June 2016.","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref_41","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/14\/5383\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T23:53:52Z","timestamp":1760140432000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/14\/5383"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,19]]},"references-count":41,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2022,7]]}},"alternative-id":["s22145383"],"URL":"https:\/\/doi.org\/10.3390\/s22145383","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7,19]]}}}