{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T08:23:59Z","timestamp":1775031839766,"version":"3.50.1"},"reference-count":29,"publisher":"MDPI AG","issue":"21","license":[{"start":{"date-parts":[[2021,10,22]],"date-time":"2021-10-22T00:00:00Z","timestamp":1634860800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Automatic ship detection provides an essential function towards maritime domain awareness for security or economic monitoring purposes. This work presents an approach for training a deep learning ship detector in Sentinel-2 multi-spectral images with few labeled examples. We design a network architecture for detecting ships with a backbone that can be pre-trained separately. By using self supervised learning, an emerging unsupervised training procedure, we learn good features on Sentinel-2 images, without requiring labeling, to initialize our network\u2019s backbone. The full network is then fine-tuned to learn to detect ships in challenging settings. We evaluated this approach versus pre-training on ImageNet and versus a classical image processing pipeline. We examined the impact of variations in the self-supervised learning step and we show that in the few-shot learning setting self-supervised pre-training achieves better results than ImageNet pre-training. When enough training data are available, our self-supervised approach is as good as ImageNet pre-training. We conclude that a better design of the self-supervised task and bigger non-annotated dataset sizes can lead to surpassing ImageNet pre-training performance without any annotation costs.<\/jats:p>","DOI":"10.3390\/rs13214255","type":"journal-article","created":{"date-parts":[[2021,10,24]],"date-time":"2021-10-24T22:07:11Z","timestamp":1635113231000},"page":"4255","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":34,"title":["Ship Detection in Sentinel 2 Multi-Spectral Images with Self-Supervised Learning"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5145-6938","authenticated-orcid":false,"given":"Alina","family":"Ciocarlan","sequence":"first","affiliation":[{"name":"IMT Atlantique, 29280 Plouzan\u00e9, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3479-9565","authenticated-orcid":false,"given":"Andrei","family":"Stoian","sequence":"additional","affiliation":[{"name":"Thales\/SIX\/ThereSiS, 91120 Palaiseau, France"}]}],"member":"1968","published-online":{"date-parts":[[2021,10,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"2687","DOI":"10.1109\/JSTARS.2016.2551730","article-title":"A Comparative Study of Operational Vessel Detectors for Maritime Surveillance Using Satellite-Borne Synthetic Aperture Radar","volume":"9","author":"Stasolla","year":"2016","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Yang, K., Ye, W., Ma, F., Li, G., and Tong, Q. (2020). A Large-Scene Deceptive Jamming Method for Space-Borne SAR Based on Time-Delay and Frequency-Shift with Template Segmentation. Remote Sens., 12.","DOI":"10.20944\/preprints201911.0340.v1"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Heiselberg, P., and Heiselberg, H. (2017). Ship-Iceberg discrimination in Sentinel-2 multispectral imagery by supervised classification. Remote Sens., 9.","DOI":"10.3390\/rs9111156"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Xie, X., Li, B., and Wei, X. (2020). Ship Detection in Multispectral Satellite Images Under Complex Environment. Remote Sens., 12.","DOI":"10.3390\/rs12050792"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Heiselberg, H. (2016). A Direct and Fast Methodology for Ship Recognition in Sentinel-2 Multispectral Imagery. Remote Sens., 8.","DOI":"10.3390\/rs8121033"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Jaiswal, A., Babu, A.R., Zadeh, M.Z., Banerjee, D., and Makedon, F. (2021). A survey on contrastive self-supervised learning. Technologies, 9.","DOI":"10.3390\/technologies9010002"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.rse.2017.12.033","article-title":"Vessel detection and classification from spaceborne optical images: A literature survey","volume":"207","author":"Kanjir","year":"2018","journal-title":"Remote Sens. Environ."},{"key":"ref_8","first-page":"145","article-title":"Ship detection and classification from optical remote sensing images: A survey","volume":"34","author":"Li","year":"2020","journal-title":"Chin. J. Aeronaut."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Zhang, S., Wu, R., Xu, K., Wang, J., and Sun, W. (2019). R-CNN-Based Ship Detection from High Resolution Remote Sensing Imagery. Remote Sens., 11.","DOI":"10.3390\/rs11060631"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Liu, Z., Yuan, L., Weng, L., and Yang, Y. (2017, January 24\u201326). A high resolution optical satellite image dataset for ship recognition and some new baselines. Proceedings of the International Conference on Pattern Recognition Applications and Methods, Porto, Portugal.","DOI":"10.5220\/0006120603240331"},{"key":"ref_11","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_12","doi-asserted-by":"crossref","unstructured":"Tang, G., Liu, S., Fujino, I., Claramunt, C., Wang, Y., and Men, S. (2020). H-YOLO: A Single-Shot Ship Detection Approach Based on Region of Interest Preselected Network. Remote Sens., 12.","DOI":"10.3390\/rs12244192"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5\u20139). U-net: Convolutional networks for biomedical image segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Karki, S., and Kulkarni, S. (2021, January 19\u201320). Ship Detection and Segmentation using Unet. Proceedings of the 2021 International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT), Bhilai, India.","DOI":"10.1109\/ICAECT49130.2021.9392463"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Tang, G., Zhuge, Y., Claramunt, C., and Men, S. (2021). N-YOLO: A SAR Ship Detection Using Noise-Classifying and Complete-Target Extraction. Remote Sens., 13.","DOI":"10.3390\/rs13050871"},{"key":"ref_16","unstructured":"Lagrange, A., De Vieilleville, F., Ruiloba, R., Le Saux, B., and Mathieu, P.P. (October, January 28). CORTEX: Open training datasets of Sentinel images: Ships (Sentinel-2) and refugee camps detection (Sentinel-1 and 2). Proceedings of the ESA EO PHI-WEEK 2020, Virtual Event."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Liu, X., Zhang, F., Hou, Z., Mian, L., Wang, Z., Zhang, J., and Tang, J. (2021). Self-supervised learning: Generative or contrastive. IEEE Trans. Knowl. Data Eng.","DOI":"10.1109\/TKDE.2021.3090866"},{"key":"ref_18","unstructured":"Purushwalkam, S., and Gupta, A. (2020). Demystifying contrastive self-supervised learning: Invariances, augmentations and dataset biases. arXiv."},{"key":"ref_19","unstructured":"Zimmermann, R.S., Sharma, Y., Schneider, S., Bethge, M., and Brendel, W. (2021). Contrastive Learning Inverts the Data Generating Process. arXiv."},{"key":"ref_20","unstructured":"Tsai, Y.H.H., Wu, Y., Salakhutdinov, R., and Morency, L.P. (2020). Self-supervised learning from a multi-view perspective. arXiv."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Doersch, C., Gupta, A., and Efros, A.A. (2015, January 7\u201313). Unsupervised visual representation learning by context prediction. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref_22","unstructured":"Tao, C., Qi, J., Lu, W., Wang, H., and Li, H. (2020). Remote sensing image scene classification with self-supervised paradigm under limited labeled samples. IEEE Geosci. Remote Sens. Lett."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Leenstra, M., Marcos, D., Bovolo, F., and Tuia, D. (2021). Self-supervised pre-training enhances change detection in Sentinel-2 imagery. arXiv.","DOI":"10.1007\/978-3-030-68787-8_42"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., and Girshick, R. (2020, January 14\u201319). Momentum contrast for unsupervised visual representation learning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"2217","DOI":"10.1109\/JSTARS.2019.2918242","article-title":"Eurosat: A novel dataset and deep learning benchmark for land use and land cover classification","volume":"12","author":"Helber","year":"2019","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Jung, H., Oh, Y., Jeong, S., Lee, C., and Jeon, T. (2021). Contrastive Self-Supervised Learning With Smoothed Representation for Remote Sensing. IEEE Geosci. Remote Sens. Lett.","DOI":"10.1109\/LGRS.2021.3069799"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., and Doll\u00e1r, P. (2017, January 22\u201329). Focal Loss for Dense Object Detection. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref_28","unstructured":"Sumbul, G., Kang, J., Kreuziger, T., Marcelino, F., Costa, H., Benevides, P., Caetano, M., and Demir, B. (2020). BigEarthNet dataset with a new class-nomenclature for remote sensing image understanding. arXiv."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Schmitt, M., Hughes, L.H., Qiu, C., and Zhu, X.X. (2019). SEN12MS\u2014A Curated Dataset of Georeferenced Multi-Spectral Sentinel-1\/2 Imagery for Deep Learning and Data Fusion. arXiv.","DOI":"10.5194\/isprs-annals-IV-2-W7-153-2019"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/21\/4255\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:21:44Z","timestamp":1760167304000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/21\/4255"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,22]]},"references-count":29,"journal-issue":{"issue":"21","published-online":{"date-parts":[[2021,11]]}},"alternative-id":["rs13214255"],"URL":"https:\/\/doi.org\/10.3390\/rs13214255","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10,22]]}}}