{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T12:23:31Z","timestamp":1764937411103,"version":"build-2065373602"},"reference-count":36,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T00:00:00Z","timestamp":1652659200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"German Federal Ministry of Education and Research","award":["13GW0203A"],"award-info":[{"award-number":["13GW0203A"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Data augmentation methods enrich datasets with augmented data to improve the performance of neural networks. Recently, automated data augmentation methods have emerged, which automatically design augmentation strategies. The existing work focuses on image classification and object detection, whereas we provide the first study on semantic image segmentation and introduce two new approaches: SmartAugment and SmartSamplingAugment. SmartAugment uses Bayesian Optimization to search a rich space of augmentation strategies and achieves new state-of-the-art performance in all semantic segmentation tasks we consider. SmartSamplingAugment, a simple parameter-free approach with a fixed augmentation strategy, competes in performance with the existing resource-intensive approaches and outperforms cheap state-of-the-art data augmentation methods. Furthermore, we analyze the impact, interaction, and importance of data augmentation hyperparameters and perform ablation studies, which confirm our design choices behind SmartAugment and SmartSamplingAugment. Lastly, we will provide our source code for reproducibility and to facilitate further research.<\/jats:p>","DOI":"10.3390\/a15050165","type":"journal-article","created":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T13:06:23Z","timestamp":1652706383000},"page":"165","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Smart(Sampling)Augment: Optimal and Efficient Data Augmentation for Semantic Segmentation"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0297-7670","authenticated-orcid":false,"given":"Misgana","family":"Negassi","sequence":"first","affiliation":[{"name":"Institute for Sustainable Systems Engineering INATECH, Albert Ludwigs University of Freiburg, 79110 Freiburg, Germany"},{"name":"Fraunhofer Institute for Physical Measurement Techniques IPM, 79110 Freiburg, Germany"}]},{"given":"Diane","family":"Wagner","sequence":"additional","affiliation":[{"name":"Institute for Sustainable Systems Engineering INATECH, Albert Ludwigs University of Freiburg, 79110 Freiburg, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3196-3876","authenticated-orcid":false,"given":"Alexander","family":"Reiterer","sequence":"additional","affiliation":[{"name":"Institute for Sustainable Systems Engineering INATECH, Albert Ludwigs University of Freiburg, 79110 Freiburg, Germany"},{"name":"Fraunhofer Institute for Physical Measurement Techniques IPM, 79110 Freiburg, Germany"}]}],"member":"1968","published-online":{"date-parts":[[2022,5,16]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"2349","DOI":"10.1007\/s00345-019-03059-0","article-title":"Application of artificial neural networks for automated analysis of cystoscopic images: A review of the current status and future prospects","volume":"38","author":"Negassi","year":"2020","journal-title":"World J. Urol."},{"key":"ref_2","first-page":"461","article-title":"Image-based 3D surface approximation of the bladder using structure-from-motion for enhanced cystoscopy based on phantom data","volume":"63","author":"Hein","year":"2018","journal-title":"Biomed. Eng. Biomed. Tech."},{"unstructured":"Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press. Available online: http:\/\/www.deeplearningbook.org.","key":"ref_3"},{"doi-asserted-by":"crossref","unstructured":"Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., and Yoo, Y. (2019). CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features. arXiv.","key":"ref_4","DOI":"10.1109\/ICCV.2019.00612"},{"unstructured":"Devries, T., and Taylor, G.W. (2017). Improved Regularization of Convolutional Neural Networks with Cutout. arXiv.","key":"ref_5"},{"doi-asserted-by":"crossref","unstructured":"Zhang, H., Ciss\u00e9, M., Dauphin, Y.N., and Lopez-Paz, D. (2017). mixup: Beyond Empirical Risk Minimization. arXiv.","key":"ref_6","DOI":"10.1007\/978-1-4899-7687-1_79"},{"unstructured":"Girshick, R., Radosavovic, I., Gkioxari, G., Doll\u00e1r, P., and He, K. (2022, April 01). Detectron. Available online: https:\/\/github.com\/facebookresearch\/detectron.","key":"ref_7"},{"unstructured":"Chen, T., Kornblith, S., Norouzi, M., and Hinton, G.E. (2020). A Simple Framework for Contrastive Learning of Visual Representations. arXiv.","key":"ref_8"},{"doi-asserted-by":"crossref","unstructured":"Nishio, M., Noguchi, S., and Fujimoto, K. (2020). Automatic Pancreas Segmentation Using Coarse-Scaled 2D Model of Deep Learning: Usefulness of Data Augmentation and Deep U-Net. Appl. Sci., 10.","key":"ref_9","DOI":"10.3390\/app10103360"},{"doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Man\u00e9, D., Vasudevan, V., and Le, Q.V. (2018). AutoAugment: Learning Augmentation Policies from Data. arXiv.","key":"ref_10","DOI":"10.1109\/CVPR.2019.00020"},{"doi-asserted-by":"crossref","unstructured":"Zoph, B., Cubuk, E.D., Ghiasi, G., Lin, T., Shlens, J., and Le, Q.V. (2019). Learning Data Augmentation Strategies for Object Detection. arXiv.","key":"ref_11","DOI":"10.1109\/CVPR.2019.00020"},{"doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Shlens, J., and Le, Q.V. (2019). RandAugment: Practical data augmentation with no separate search. arXiv.","key":"ref_12","DOI":"10.1109\/CVPRW50498.2020.00359"},{"unstructured":"Jaderberg, M., Dalibard, V., Osindero, S., Czarnecki, W.M., Donahue, J., Razavi, A., Vinyals, O., Green, T., Dunning, I., and Simonyan, K. (2017). Population Based Training of Neural Networks. arXiv.","key":"ref_13"},{"unstructured":"Pereira, F., Burges, C.J.C., Bottou, L., and Weinberger, K.Q. (2012). Practical Bayesian Optimization of Machine Learning Algorithms. Advances in Neural Information Processing Systems, Curran Associates, Inc.","key":"ref_14"},{"unstructured":"Falkner, S., Klein, A., and Hutter, F. (2018). BOHB: Robust and Efficient Hyperparameter Optimization at Scale. arXiv.","key":"ref_15"},{"doi-asserted-by":"crossref","unstructured":"M\u00fcller, S.G., and Hutter, F. (2021). TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentation. arXiv.","key":"ref_16","DOI":"10.1109\/ICCV48922.2021.00081"},{"unstructured":"Pereira, F., Burges, C.J.C., Bottou, L., and Weinberger, K.Q. (2012). ImageNet Classification with Deep Convolutional Neural Networks. Advances in Neural Information Processing Systems, Curran Associates, Inc.","key":"ref_17"},{"doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2015). Deep Residual Learning for Image Recognition. arXiv.","key":"ref_18","DOI":"10.1109\/CVPR.2016.90"},{"doi-asserted-by":"crossref","unstructured":"Han, D., Kim, J., and Kim, J. (2016). Deep Pyramidal Residual Networks. arXiv.","key":"ref_19","DOI":"10.1109\/CVPR.2017.668"},{"key":"ref_20","first-page":"1058","article-title":"Regularization of Neural Networks using DropConnect","volume":"Volume 28","author":"Dasgupta","year":"2013","journal-title":"Proceedings of the 30th International Conference on Machine Learning"},{"unstructured":"Zhong, Z., Zheng, L., Kang, G., Li, S., and Yang, Y. (2017). Random Erasing Data Augmentation. arXiv.","key":"ref_21"},{"unstructured":"Antoniou, A., Storkey, A., and Edwards, H. (2018). Data Augmentation Generative Adversarial Networks. arXiv.","key":"ref_22"},{"unstructured":"Perez, L., and Wang, J. (2017). The Effectiveness of Data Augmentation in Image Classification using Deep Learning. arXiv.","key":"ref_23"},{"key":"ref_24","first-page":"2731","article-title":"Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules","volume":"Volume 97","author":"Chaudhuri","year":"2019","journal-title":"Proceedings of the 36th International Conference on Machine Learning"},{"unstructured":"Lim, S., Kim, I., Kim, T., Kim, C., and Kim, S. (2019). Fast AutoAugment. arXiv.","key":"ref_25"},{"unstructured":"Zhang, X., Wang, Q., Zhang, J., and Zhong, Z. (2019). Adversarial AutoAugment. arXiv.","key":"ref_26"},{"key":"ref_27","first-page":"9","article-title":"Efficient BackProp","volume":"Volume 7700","author":"Montavon","year":"2012","journal-title":"Neural Networks: Tricks of the Trade"},{"unstructured":"Chen, L., Papandreou, G., Schroff, F., and Adam, H. (2017). Rethinking Atrous Convolution for Semantic Image Segmentation. arXiv.","key":"ref_28"},{"unstructured":"Tao, A., Sapra, K., and Catanzaro, B. (2020). Hierarchical Multi-Scale Attention for Semantic Segmentation. arXiv.","key":"ref_29"},{"key":"ref_30","first-page":"281","article-title":"Random Search for Hyper-Parameter Optimization","volume":"13","author":"Bergstra","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref_31","first-page":"234","article-title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","volume":"Volume 9351","author":"Ronneberger","year":"2015","journal-title":"Medical Image Computing and Computer-Assisted Intervention (MICCAI)"},{"unstructured":"Ruder, S. (2016). An overview of gradient descent optimization algorithms. arXiv.","key":"ref_32"},{"unstructured":"Loshchilov, I., and Hutter, F. (2016). SGDR: Stochastic Gradient Descent with Restarts. arXiv.","key":"ref_33"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1231","DOI":"10.1177\/0278364913491297","article-title":"Vision meets Robotics: The KITTI Dataset","volume":"32","author":"Geiger","year":"2013","journal-title":"Int. J. Robot. Res."},{"doi-asserted-by":"crossref","unstructured":"Cardona, A., Saalfeld, S., Preibisch, S., Schmid, B., Cheng, A., Pulokas, J., Tomancak, P., and Hartenstein, V. (2010). An integrated micro-and macroarchitectural analysis of the Drosophila brain by computer-assisted serial section electron microscopy. PLoS Biol., 8.","key":"ref_35","DOI":"10.1371\/journal.pbio.1000502"},{"key":"ref_36","first-page":"754","article-title":"An Efficient Approach for Assessing Hyperparameter Importance","volume":"Volume 32","author":"Xing","year":"2014","journal-title":"Proceedings of the 31st International Conference on Machine Learning"}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/15\/5\/165\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T23:11:12Z","timestamp":1760137872000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/15\/5\/165"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,16]]},"references-count":36,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2022,5]]}},"alternative-id":["a15050165"],"URL":"https:\/\/doi.org\/10.3390\/a15050165","relation":{},"ISSN":["1999-4893"],"issn-type":[{"type":"electronic","value":"1999-4893"}],"subject":[],"published":{"date-parts":[[2022,5,16]]}}}