{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T16:02:08Z","timestamp":1782403328473,"version":"3.54.5"},"reference-count":56,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2020,1,7]],"date-time":"2020-01-07T00:00:00Z","timestamp":1578355200000},"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>Accurate automated segmentation of remote sensing data could benefit applications from land cover mapping and agricultural monitoring to urban development surveyal and disaster damage assessment. While convolutional neural networks (CNNs) achieve state-of-the-art accuracy when segmenting natural images with huge labeled datasets, their successful translation to remote sensing tasks has been limited by low quantities of ground truth labels, especially fully segmented ones, in the remote sensing domain. In this work, we perform cropland segmentation using two types of labels commonly found in remote sensing datasets that can be considered sources of \u201cweak supervision\u201d: (1) labels comprised of single geotagged points and (2) image-level labels. We demonstrate that (1) a U-Net trained on a single labeled pixel per image and (2) a U-Net image classifier transferred to segmentation can outperform pixel-level algorithms such as logistic regression, support vector machine, and random forest. While the high performance of neural networks is well-established for large datasets, our experiments indicate that U-Nets trained on weak labels outperform baseline methods with as few as 100 labels. Neural networks, therefore, can combine superior classification performance with efficient label usage, and allow pixel-level labels to be obtained from image labels.<\/jats:p>","DOI":"10.3390\/rs12020207","type":"journal-article","created":{"date-parts":[[2020,1,8]],"date-time":"2020-01-08T03:59:57Z","timestamp":1578455997000},"page":"207","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":205,"title":["Weakly Supervised Deep Learning for Segmentation of Remote Sensing Imagery"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4618-5675","authenticated-orcid":false,"given":"Sherrie","family":"Wang","sequence":"first","affiliation":[{"name":"Institute for Computational and Mathematical Engineering, Stanford University, Stanford, CA 94305, USA"},{"name":"Department of Earth System Science, Stanford University, Stanford, CA 94305, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"William","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Stanford University, Stanford, CA 94305, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0820-2753","authenticated-orcid":false,"given":"Sang Michael","family":"Xie","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Stanford University, Stanford, CA 94305, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"George","family":"Azzari","sequence":"additional","affiliation":[{"name":"Department of Earth System Science, Stanford University, Stanford, CA 94305, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David B.","family":"Lobell","sequence":"additional","affiliation":[{"name":"Department of Earth System Science, Stanford University, Stanford, CA 94305, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2020,1,7]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"850","DOI":"10.1126\/science.1244693","article-title":"High-Resolution Global Maps of 21st-Century Forest Cover Change","volume":"342","author":"Hansen","year":"2013","journal-title":"Science"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1016\/j.isprsjprs.2017.10.012","article-title":"Breaking new ground in mapping human settlements from space \u2013 The Global Urban Footprint","volume":"134","author":"Esch","year":"2017","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1029\/97RG02669","article-title":"Monitoring ice sheet behavior from space","volume":"36","author":"Bindschadler","year":"1998","journal-title":"Rev. Geophys."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Amit, S.N.K.B., Shiraishi, S., Inoshita, T., and Aoki, Y. (2016, January 10\u201315). Analysis of satellite images for disaster detection. Proceedings of the 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Beijing, China.","DOI":"10.1109\/IGARSS.2016.7730352"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1915","DOI":"10.1109\/TPAMI.2012.231","article-title":"Learning Hierarchical Features for Scene Labeling","volume":"35","author":"Farabet","year":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Noh, H., Hong, S., and Han, B. (2015, January 11\u201318). Learning Deconvolution Network for Semantic Segmentation. Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), Las Condes, Chile.","DOI":"10.1109\/ICCV.2015.178"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Navab, N., Hornegger, J., Wells, W.M., and Frangi, A.F. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015, Springer International Publishing.","DOI":"10.1007\/978-3-319-24571-3"},{"key":"ref_8","unstructured":"Ferrari, V., Hebert, M., Sminchisescu, C., and Weiss, Y. (2018). Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation. Computer Vision\u2014ECCV 2018, Springer International Publishing."},{"key":"ref_9","unstructured":"Chen, L., Papandreou, G., Schroff, F., and Adam, H. (2017). Rethinking Atrous Convolution for Semantic Image Segmentation. arXiv."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","article-title":"The Pascal Visual Object Classes (VOC) Challenge","volume":"88","author":"Everingham","year":"2010","journal-title":"Int. J. Comput. Vis."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Fleet, D., Pajdla, T., Schiele, B., and Tuytelaars, T. (2014). Microsoft COCO: Common Objects in Context. Computer Vision\u2014ECCV 2014, Springer International Publishing.","DOI":"10.1007\/978-3-319-10590-1"},{"key":"ref_12","unstructured":"Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., and Schiele, B. (July, January 26). The Cityscapes Dataset for Semantic Urban Scene Understanding. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Neuhold, G., Ollmann, T., Bulo, S., and Kontschieder, P. (2017, January 22\u201329). The Mapillary Vistas Dataset for Semantic Understanding of Street Scenes. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.534"},{"key":"ref_14","unstructured":"Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1016\/j.asoc.2018.05.018","article-title":"A survey on deep learning techniques for image and video semantic segmentation","volume":"70","author":"Oprea","year":"2018","journal-title":"Appl. Soft Comput."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"790","DOI":"10.1126\/science.aaf7894","article-title":"Combining satellite imagery and machine learning to predict poverty","volume":"353","author":"Jean","year":"2016","journal-title":"Science"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1093\/nsr\/nwx106","article-title":"A brief introduction to weakly supervised learning","volume":"5","author":"Zhou","year":"2017","journal-title":"Natl. Sci. Rev."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1016\/j.rse.2019.04.016","article-title":"Smallholder maize area and yield mapping at national scales with Google Earth Engine","volume":"228","author":"Jin","year":"2019","journal-title":"Remote Sens. Environ."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1016\/j.isprsjprs.2017.01.019","article-title":"Automated cropland mapping of continental Africa using Google Earth Engine cloud computing","volume":"126","author":"Xiong","year":"2017","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_20","unstructured":"USDA National Agricultural Statistics Service Cropland Data Layer (2018, March 01). Published Crop-Specific Data Layer. Available online: https:\/\/nassgeodata.gmu.edu\/CropScape\/."},{"key":"ref_21","unstructured":"Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N.D., and Weinberger, K.Q. (2014). Learning Deep Features for Scene Recognition using Places Database. Advances in Neural Information Processing Systems 27, Curran Associates, Inc."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Ru\u00dfwurm, M., and K\u00f6rner, M. (2018). Multi-Temporal Land Cover Classification with Sequential Recurrent Encoders. ISPRS Int. J. Geo-Inf., 7.","DOI":"10.3390\/ijgi7040129"},{"key":"ref_23","unstructured":"Rustowicz, R., Cheong, R., Wang, L., Ermon, S., Burke, M., and Lobell, D.B. (2019, January 16\u201320). Semantic Segmentation of Crop Type in Africa: A Novel Dataset and Analysis of Deep Learning Methods. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Long Beach, CA, USA."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1016\/j.rse.2019.03.039","article-title":"A cloud detection algorithm for satellite imagery based on deep learning","volume":"229","author":"Jeppesen","year":"2019","journal-title":"Remote Sens. Environ."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Dr\u00f6nner, J., Korfhage, N., Egli, S., M\u00fchling, M., Thies, B., Bendix, J., Freisleben, B., and Seeger, B. (2018). Fast Cloud Segmentation Using Convolutional Neural Networks. Remote Sens., 10.","DOI":"10.3390\/rs10111782"},{"key":"ref_26","unstructured":"Zhang, A., Liu, X., Gros, A., and Tiecke, T. (2017). Building Detection from Satellite Images on a Global Scale. arXiv."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Sun, Y., Zhang, X., Zhao, X., and Xin, Q. (2018). Extracting Building Boundaries from High Resolution Optical Images and LiDAR Data by Integrating the Convolutional Neural Network and the Active Contour Model. Remote Sens., 10.","DOI":"10.3390\/rs10091459"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Yi, Y., Zhang, Z., Zhang, W., Zhang, C., Li, W., and Zhao, T. (2019). Semantic Segmentation of Urban Buildings from VHR Remote Sensing Imagery Using a Deep Convolutional Neural Network. Remote Sens., 11.","DOI":"10.3390\/rs11151774"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Diakogiannis, F.I., Waldner, F., Caccetta, P., and Wu, C. (2019). ResUNet-a: A deep learning framework for semantic segmentation of remotely sensed data. arXiv.","DOI":"10.1016\/j.isprsjprs.2020.01.013"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Hwang, J.I., and Jung, H.S. (2018). Automatic Ship Detection Using the Artificial Neural Network and Support Vector Machine from X-Band SAR Satellite Images. Remote Sens., 10.","DOI":"10.3390\/rs10111799"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1867","DOI":"10.1109\/LGRS.2018.2864342","article-title":"Road Segmentation in SAR Satellite Images With Deep Fully Convolutional Neural Networks","volume":"15","author":"Henry","year":"2018","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Panboonyuen, T., Jitkajornwanich, K., Lawawirojwong, S., Srestasathiern, P., and Vateekul, P. (2017). Road Segmentation of Remotely-Sensed Images Using Deep Convolutional Neural Networks with Landscape Metrics and Conditional Random Fields. Remote Sens., 9.","DOI":"10.20944\/preprints201706.0012.v2"},{"key":"ref_33","unstructured":"(2019, April 30). ISPRS Test Project on Urban Classification, 3D Building Reconstruction and Semantic Labeling. Available online: http:\/\/www2.isprs.org\/commissions\/comm3\/wg4\/tests.html."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Maggiori, E., Tarabalka, Y., Charpiat, G., and Alliez, P. (2017, January 23\u201328). Can Semantic Labeling Methods Generalize to Any City? The Inria Aerial Image Labeling Benchmark. Proceedings of the IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Fort Worth, TX, USA.","DOI":"10.1109\/IGARSS.2017.8127684"},{"key":"ref_35","unstructured":"(2019, April 30). Dstl Satellite Imagery Feature Detection. Available online: https:\/\/www.kaggle.com\/c\/dstl-satellite-imagery-feature-detection."},{"key":"ref_36","unstructured":"(2019, April 30). CrowdAnalytix Agricultural Crop Cover Classification Challenge. Available online: https:\/\/www.crowdanalytix.com\/contests\/agricultural-crop-cover-classification-challenge."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Demir, I., Koperski, K., Lindenbaum, D., Pang, G., Huang, J., Basu, S., Hughes, F., Tuia, D., and Raska, R. (2018, January 19\u201321). DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Salt Lake City, UT, USA.","DOI":"10.1109\/CVPRW.2018.00031"},{"key":"ref_38","unstructured":"Sumbul, G., Charfuelan, M., Demir, B., and Markl, V. (August, January 28). Bigearthnet: A Large-Scale Benchmark Archive for Remote Sensing Image Understanding. Proceedings of the IEEE International Conference on Geoscience and Remote Sensing Symposium, Yokohama, Japan."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"6054","DOI":"10.1109\/TGRS.2017.2719738","article-title":"Learning Aerial Image Segmentation From Online Maps","volume":"55","author":"Kaiser","year":"2017","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.isprsjprs.2018.04.014","article-title":"Algorithms for semantic segmentation of multispectral remote sensing imagery using deep learning","volume":"145","author":"Kemker","year":"2018","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1080\/2150704X.2018.1557787","article-title":"Semi-supervised deep learning for hyperspectral image classification","volume":"10","author":"Kang","year":"2019","journal-title":"Remote Sens. Lett."},{"key":"ref_42","unstructured":"Hong, S., Noh, H., and Han, B. (2015, January 7\u201312). Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation. Proceedings of the 28th International Conference on Neural Information Processing Systems, Montreal, QC, Canada."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Pinheiro, P.O., and Collobert, R. (2015, January 7\u201312). From image-level to pixel-level labeling with Convolutional Networks. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298780"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1016\/j.isprsjprs.2018.07.017","article-title":"A 30-m landsat-derived cropland extent product of Australia and China using random forest machine learning algorithm on Google Earth Engine cloud computing platform","volume":"144","author":"Teluguntla","year":"2018","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Xiong, J., Thenkabail, P.S., Tilton, J.C., Gumma, M.K., Teluguntla, P., Oliphant, A., Congalton, R.G., Yadav, K., and Gorelick, N. (2017). Nominal 30-m Cropland Extent Map of Continental Africa by Integrating Pixel-Based and Object-Based Algorithms Using Sentinel-2 and Landsat-8 Data on Google Earth Engine. Remote Sens., 9.","DOI":"10.3390\/rs9101065"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1016\/j.rse.2017.10.005","article-title":"Sentinel-2 cropland mapping using pixel-based and object-based time-weighted dynamic time warping analysis","volume":"204","author":"Belgiu","year":"2018","journal-title":"Remote Sens. Environ."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1016\/j.rse.2014.02.001","article-title":"Landsat-8: Science and product vision for terrestrial global change research","volume":"145","author":"Roy","year":"2014","journal-title":"Remote Sens. Environ."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"438","DOI":"10.1016\/j.rse.2014.10.009","article-title":"Cloud cover throughout the agricultural growing season: Impacts on passive optical earth observations","volume":"156","author":"Whitcraft","year":"2015","journal-title":"Remote Sens. Environ."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"12356","DOI":"10.3390\/rs70912356","article-title":"Assessment of an Operational System for Crop Type Map Production Using High Temporal and Spatial Resolution Satellite Optical Imagery","volume":"7","author":"Inglada","year":"2015","journal-title":"Remote Sens."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"294","DOI":"10.1016\/j.patrec.2005.08.011","article-title":"Random Forests for land cover classification","volume":"27","author":"Gislason","year":"2006","journal-title":"Pattern Recognit. Lett."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1016\/j.rse.2017.05.025","article-title":"Landsat-based classification in the cloud: An opportunity for a paradigm shift in land cover monitoring","volume":"202","author":"Azzari","year":"2017","journal-title":"Remote Sens. Environ."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"421","DOI":"10.5721\/EuJRS20124535","article-title":"Evaluation of random forest method for agricultural crop classification","volume":"45","author":"Ok","year":"2012","journal-title":"Eur. J. Remote Sens."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/j.isprsjprs.2016.03.008","article-title":"Optical remotely sensed time series data for land cover classification: A review","volume":"116","author":"Gomez","year":"2016","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_55","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_56","unstructured":"Glorot, X., and Bengio, Y. (2010, January 13\u201315). Understanding the difficulty of training deep feedforward neural networks. Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, Sardinia, Italy."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/12\/2\/207\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T13:42:26Z","timestamp":1760362946000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/12\/2\/207"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1,7]]},"references-count":56,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2020,1]]}},"alternative-id":["rs12020207"],"URL":"https:\/\/doi.org\/10.3390\/rs12020207","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,1,7]]}}}