{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T17:07:03Z","timestamp":1776100023012,"version":"3.50.1"},"reference-count":37,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2023,6,28]],"date-time":"2023-06-28T00:00:00Z","timestamp":1687910400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Natural Science Foundation of China","award":["61871414"],"award-info":[{"award-number":["61871414"]}]},{"name":"National Natural Science Foundation of China","award":["2019-JCJQ-ZD-324"],"award-info":[{"award-number":["2019-JCJQ-ZD-324"]}]},{"name":"Military Science and Technology Commission","award":["61871414"],"award-info":[{"award-number":["61871414"]}]},{"name":"Military Science and Technology Commission","award":["2019-JCJQ-ZD-324"],"award-info":[{"award-number":["2019-JCJQ-ZD-324"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Numerous works have explored deep models for the classification of high-resolution natural images. However, limited investigation has been made into a deep classification for low-resolution synthetic aperture radar (SAR) images, which is a challenging yet important task in the field of remote sensing. Existing work adopted ROC\u2013VGG, which has a huge amount of parameters, thus limiting its application in practical deployment. It remains unclear whether the techniques developed in high-resolution natural images to make the model lightweight can be effective for low-resolution SAR images. Therefore, with prior work as the baseline, this work conducts an empirical study, testing three popular lightweight techniques: (1) channel attention module; (2) spatial attention module; (3) multi-stream head. Our empirical results show that these lightweight techniques in the high-resolution natural image domain can also be effective in the low-resolution SAR domain. We reduce the parameters from 9.2M to 0.17M while improving the performance from 94.8% to 96.8%.<\/jats:p>","DOI":"10.3390\/rs15133312","type":"journal-article","created":{"date-parts":[[2023,6,29]],"date-time":"2023-06-29T01:15:47Z","timestamp":1688001347000},"page":"3312","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Towards Lightweight Deep Classification for Low-Resolution Synthetic Aperture Radar (SAR) Images: An Empirical Study"],"prefix":"10.3390","volume":"15","author":[{"given":"Sheng","family":"Zheng","sequence":"first","affiliation":[{"name":"Science and Technology on Electromechanical Dynamic Control Laboratory, Beijing Institute of Technology, Beijing 100081, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6448-4839","authenticated-orcid":false,"given":"Xinhong","family":"Hao","sequence":"additional","affiliation":[{"name":"Science and Technology on Electromechanical Dynamic Control Laboratory, Beijing Institute of Technology, Beijing 100081, China"}]},{"given":"Chaoning","family":"Zhang","sequence":"additional","affiliation":[{"name":"Science and Technology on Electromechanical Dynamic Control Laboratory, Beijing Institute of Technology, Beijing 100081, China"}]},{"given":"Wen","family":"Zhou","sequence":"additional","affiliation":[{"name":"Science and Technology on Electromechanical Dynamic Control Laboratory, Beijing Institute of Technology, Beijing 100081, China"}]},{"given":"Lefan","family":"Duan","sequence":"additional","affiliation":[{"name":"Science and Technology on Electromechanical Dynamic Control Laboratory, Beijing Institute of Technology, Beijing 100081, China"}]}],"member":"1968","published-online":{"date-parts":[[2023,6,28]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Lu, J. (2019). Design Technology of Synthetic Aperture Radar, John Wiley & Sons.","DOI":"10.1002\/9781119564621"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1109\/MGRS.2021.3113982","article-title":"Motion compensation\/autofocus in airborne synthetic aperture radar: A review","volume":"10","author":"Chen","year":"2021","journal-title":"IEEE Geosci. Remote Sens. Mag."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"10835","DOI":"10.1109\/JSTARS.2021.3121405","article-title":"Multireceiver SAS imagery based on monostatic conversion","volume":"14","author":"Zhang","year":"2021","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Choi, H.m., Yang, H.s., and Seong, W.j. (2021). Compressive underwater sonar imaging with synthetic aperture processing. Remote Sens., 13.","DOI":"10.3390\/rs13101924"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Vint, D., Anderson, M., Yang, Y., Ilioudis, C., Di Caterina, G., and Clemente, C. (2021). Automatic target recognition for low resolution foliage penetrating SAR images using CNNs and GANs. Remote Sens., 13.","DOI":"10.3390\/rs13040596"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Zagoruyko, S., and Komodakis, N. (2016). Wide residual networks. arXiv.","DOI":"10.5244\/C.30.87"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., and Sun, G. (2018, January 18\u201323). Squeeze-and-excitation networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., and Kweon, I.S. (2018, January 8\u201314). Cbam: Convolutional block attention module. Proceedings of the European Conference on Computer Vision (ECCV), V), Munich, Germany.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"851","DOI":"10.1007\/s00138-018-0994-z","article-title":"Driving behaviour recognition from still images by using multi-stream fusion CNN","volume":"30","author":"Hu","year":"2019","journal-title":"Mach. Vis. Appl."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Chen, D., Zhang, S., Ouyang, W., Yang, J., and Tai, Y. (2018, January 8\u201314). Person search via a mask-guided two-stream cnn model. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01234-2_45"},{"key":"ref_12","first-page":"1","article-title":"SAR target recognition based on efficient fully convolutional attention block CNN","volume":"19","author":"Li","year":"2020","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"140512","DOI":"10.1109\/ACCESS.2021.3118034","article-title":"Synthetic aperture radar SAR image target recognition algorithm based on attention mechanism","volume":"9","author":"Shi","year":"2021","journal-title":"IEEE Access"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"9004","DOI":"10.1109\/JSTARS.2022.3206901","article-title":"SAR Target Classification Based on Multiscale Attention Super-Class Network","volume":"15","author":"Wang","year":"2022","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_15","first-page":"1","article-title":"Convolutional neural network with attention mechanism for SAR automatic target recognition","volume":"19","author":"Zhang","year":"2020","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"4806","DOI":"10.1109\/TGRS.2016.2551720","article-title":"Target classification using the deep convolutional networks for SAR images","volume":"54","author":"Chen","year":"2016","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Zhao, P., Liu, K., Zou, H., and Zhen, X. (2018). Multi-stream convolutional neural network for SAR automatic target recognition. Remote Sens., 10.","DOI":"10.3390\/rs10091473"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"667","DOI":"10.1109\/LGRS.2020.2983718","article-title":"Lightweight two-stream convolutional neural network for SAR target recognition","volume":"18","author":"Huang","year":"2020","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_19","first-page":"1","article-title":"SAR automatic target recognition method based on multi-stream complex-valued networks","volume":"60","author":"Zeng","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1145\/3422622","article-title":"Generative adversarial networks","volume":"63","author":"Goodfellow","year":"2020","journal-title":"Commun. ACM"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"113999","DOI":"10.1109\/ACCESS.2019.2935167","article-title":"Integrated GANs: Semi-supervised SAR target recognition","volume":"7","author":"Gao","year":"2019","journal-title":"IEEE Access"},{"key":"ref_22","first-page":"1","article-title":"A high-quality multicategory SAR images generation method with multiconstraint GAN for ATR","volume":"19","author":"Du","year":"2021","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"7525","DOI":"10.1109\/JSEN.2019.2915379","article-title":"Semi-supervised SAR ATR via multi-discriminator generative adversarial network","volume":"19","author":"Zheng","year":"2019","journal-title":"IEEE Sensors J."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"39608","DOI":"10.1109\/ACCESS.2021.3064362","article-title":"Target recognition of SAR image based on CN-GAN and CNN in complex environment","volume":"9","author":"Mao","year":"2021","journal-title":"IEEE Access"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Mao, X., Li, Q., Xie, H., Lau, R.Y., Wang, Z., and Paul Smolley, S. (2017, January 22\u201329). Least squares generative adversarial networks. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., and Efros, A.A. (2017, January 21\u201326). Image-to-image translation with conditional adversarial networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1145\/3065386","article-title":"Imagenet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2017","journal-title":"Commun. ACM"},{"key":"ref_28","unstructured":"Radford, A., Metz, L., and Chintala, S. (2015). Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv."},{"key":"ref_29","unstructured":"Brock, A., Donahue, J., and Simonyan, K. (2018). Large scale GAN training for high fidelity natural image synthesis. arXiv."},{"key":"ref_30","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., and Hochreiter, S. (2017, January 4). Gans trained by a two time-scale update rule converge to a local nash equilibrium. Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_31","first-page":"160","article-title":"A challenge problem for detection of targets in foliage","volume":"Volume 6237","author":"Lundberg","year":"2006","journal-title":"Proceedings of the Algorithms for Synthetic Aperture Radar Imagery XIII"},{"key":"ref_32","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015, January 7\u201312). Going deeper with convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref_34","unstructured":"Smith, S.L., Kindermans, P.J., Ying, C., and Le, Q.V. (2017). Don\u2019t decay the learning rate, increase the batch size. arXiv."},{"key":"ref_35","unstructured":"Keskar, N.S., Mudigere, D., Nocedal, J., Smelyanskiy, M., and Tang, P.T.P. (2016). On large-batch training for deep learning: Generalization gap and sharp minima. arXiv."},{"key":"ref_36","unstructured":"Nielsen, M.A. (2015). Neural Networks and Deep Learning, Determination Press."},{"key":"ref_37","unstructured":"Recht, B., Roelofs, R., Schmidt, L., and Shankar, V. (2019, January 9\u201315). Do imagenet classifiers generalize to imagenet?. Proceedings of the International Conference on Machine Learning, Long Beach, CA, USA."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/13\/3312\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T20:02:48Z","timestamp":1760126568000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/13\/3312"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,28]]},"references-count":37,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2023,7]]}},"alternative-id":["rs15133312"],"URL":"https:\/\/doi.org\/10.3390\/rs15133312","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,28]]}}}