{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T23:10:53Z","timestamp":1771024253024,"version":"3.50.1"},"reference-count":19,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2020,12,23]],"date-time":"2020-12-23T00:00:00Z","timestamp":1608681600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61901446"],"award-info":[{"award-number":["61901446"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>The random cropping data augmentation method is widely used to train convolutional neural network (CNN)-based target detectors to detect targets in optical images (e.g., COCO datasets). It can expand the scale of the dataset dozens of times while consuming only a small amount of calculations when training the neural network detector. In addition, random cropping can also greatly enhance the spatial robustness of the model, because it can make the same target appear in different positions of the sample image. Nowadays, random cropping and random flipping have become the standard configuration for those tasks with limited training data, which makes it natural to introduce them into the training of CNN-based synthetic aperture radar (SAR) image ship detectors. However, in this paper, we show that the introduction of traditional random cropping methods directly in the training of the CNN-based SAR image ship detector may generate a lot of noise in the gradient during back propagation, which hurts the detection performance. In order to eliminate the noise in the training gradient, a simple and effective training method based on feature map mask is proposed. Experiments prove that the proposed method can effectively eliminate the gradient noise introduced by random cropping and significantly improve the detection performance under a variety of evaluation indicators without increasing inference cost.<\/jats:p>","DOI":"10.3390\/rs13010034","type":"journal-article","created":{"date-parts":[[2020,12,24]],"date-time":"2020-12-24T00:53:31Z","timestamp":1608771211000},"page":"34","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":30,"title":["Rethinking the Random Cropping Data Augmentation Method Used in the Training of CNN-Based SAR Image Ship Detector"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5620-7615","authenticated-orcid":false,"given":"Rong","family":"Yang","sequence":"first","affiliation":[{"name":"Space Microwave Remote Sensing System Department, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, China"},{"name":"School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing 100039, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9850-7015","authenticated-orcid":false,"given":"Robert","family":"Wang","sequence":"additional","affiliation":[{"name":"Space Microwave Remote Sensing System Department, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, China"}]},{"given":"Yunkai","family":"Deng","sequence":"additional","affiliation":[{"name":"Space Microwave Remote Sensing System Department, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, China"}]},{"given":"Xiaoxue","family":"Jia","sequence":"additional","affiliation":[{"name":"Space Microwave Remote Sensing System Department, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, China"}]},{"given":"Heng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Space Microwave Remote Sensing System Department, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, China"}]}],"member":"1968","published-online":{"date-parts":[[2020,12,23]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27\u201330). You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., and Berg, A.C. (2016). Ssd: Single shot multi box detector. European Conference On computer Vision, Springer.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref_3","unstructured":"Ren, S., He, K., Girshick, R., and Sun, J. Faster r-cnn: Towards real-time object detection with region proposal networks. Proceedings of the Advances in Neural information Processing Systems."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"8333","DOI":"10.1109\/TGRS.2019.2920534","article-title":"Drbox-v2: An improved detector with rotatable boxes for target detection in sar images","volume":"57","author":"An","year":"2019","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Wang, Y., Wang, C., Zhang, H., Dong, Y., and Wei, S. (2019). Automatic ship detection based on retinanet using multi-resolution gaofen-3 imagery. Remote Sens., 11.","DOI":"10.3390\/rs11050531"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Wei, S., Su, H., Ming, J., Wang, C., Yan, M., Kumar, D., Shi, J., and Zhang, X. (2020). Precise and robust ship detection for high-resolution sar imagery based on hr-sdnet. Remote Sens., 12.","DOI":"10.3390\/rs12010167"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Zhang, T., Zhang, X., Shi, J., and Wei, S. (2019). Depth wise separable convolution neural network for high-speed sar ship detection. Remote Sens., 11.","DOI":"10.3390\/rs11212483"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"8983","DOI":"10.1109\/TGRS.2019.2923988","article-title":"Dense attention pyramid networks for multi-scale ship detection in sar images","volume":"Volume 57","author":"Cui","year":"2019","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Wu, X., Sahoo, D., and Hoi, S.C. (2020). Recent advances in deep learning for object detection. Neurocomputing.","DOI":"10.1016\/j.neucom.2020.01.085"},{"key":"ref_10","unstructured":"Bochkovskiy, A., Wang, C.-Y., and Liao, H.-Y.M. (2020). Yolov4: Optimal speed and accuracy of object detection. arXiv, Available online: https:\/\/arxiv.org\/abs\/2004.10934."},{"key":"ref_11","unstructured":"Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., and Yoo, Y. (November, January 27). Cutmix: Regularization strategy to train strong classifiers with localizable features. Proceedings of the IEEE International Conference on Computer Vision, Seoul, Korea."},{"key":"ref_12","unstructured":"Zhou, X., Wang, D., and Kr\u00e4henb\u00fchl, P. (2019). Objects as points. arXiv, Available online: https:\/\/arxiv.org\/abs\/1904.07850."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"104848","DOI":"10.1109\/ACCESS.2019.2930939","article-title":"A deep neural network based on an attention mechanism for sar ship detection in multi scale and complex scenarios","volume":"7","author":"Chen","year":"2019","journal-title":"IEEE Access"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Yu, F., Wang, D., Shelhamer, E., and Darrell, T. (2018, January 18\u201323). Deep layer aggregation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00255"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Liu, Z., Zheng, T., Xu, G., Yang, Z., Liu, H., and Cai, D. (2020). Training-Time-Friendly Network for Real-Time Object Detection, AAAI.","DOI":"10.1609\/aaai.v34i07.6838"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., and Dollar, P. (2017, January 22\u201329). Focal loss for dense object detection. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"120234","DOI":"10.1109\/ACCESS.2020.3005861","article-title":"Hrsid: A high-resolution sar images dataset for ship detection and instan cesegmentation","volume":"8","author":"Wei","year":"2020","journal-title":"IEEE Access"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Li, J., Qu, C., and Shao, J. (2017, January 13\u201314). Ship detection in sar images based on an improved faster r-cnn. Proceedings of the 2017 SAR in Big Data Era: Models, Methods and Applications (BIGSARDATA), Beijing, China.","DOI":"10.1109\/BIGSARDATA.2017.8124934"},{"key":"ref_19","unstructured":"Everingham, M., van Gool, L., Williams, C.K., Winn, J., and Zisserman, A. (2020, April 29). The Pascal Visual Object Classes Challenge 2007 (voc2007) Results. Available online: http:\/\/host.robots.ox.ac.uk\/pascal\/VOC\/voc2007\/."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/1\/34\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T10:49:05Z","timestamp":1760179745000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/1\/34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,23]]},"references-count":19,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2021,1]]}},"alternative-id":["rs13010034"],"URL":"https:\/\/doi.org\/10.3390\/rs13010034","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,12,23]]}}}