{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T16:10:55Z","timestamp":1775146255572,"version":"3.50.1"},"reference-count":47,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2019,5,14]],"date-time":"2019-05-14T00:00:00Z","timestamp":1557792000000},"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>Learning classification models require sufficiently labeled training samples, however, collecting labeled samples for every new problem is time-consuming and costly. An alternative approach is to transfer knowledge from one problem to another, which is called transfer learning. Domain adaptation (DA) is a type of transfer learning that aims to find a new latent space where the domain discrepancy between the source and the target domain is negligible. In this work, we propose an unsupervised DA technique called domain adversarial neural networks (DANNs), composed of a feature extractor, a class predictor, and domain classifier blocks, for large-scale land cover classification. Contrary to the traditional methods that perform representation and classifier learning in separate stages, DANNs combine them into a single stage, thereby learning a new representation of the input data that is both domain-invariant and discriminative. Once trained, the classifier of a DANN can be used to predict both source and target domain labels. Additionally, we also modify the domain classifier of a DANN to evaluate its suitability for multi-target domain adaptation problems. Experimental results obtained for both single and multiple target DA problems show that the proposed method provides a performance gain of up to 40%.<\/jats:p>","DOI":"10.3390\/rs11101153","type":"journal-article","created":{"date-parts":[[2019,5,14]],"date-time":"2019-05-14T10:42:33Z","timestamp":1557830553000},"page":"1153","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":32,"title":["Domain Adversarial Neural Networks for Large-Scale Land Cover Classification"],"prefix":"10.3390","volume":"11","author":[{"given":"Mesay Belete","family":"Bejiga","sequence":"first","affiliation":[{"name":"Department of Information Engineering and Computer Science, University of Trento, Via Sommarive, 9, I-38123 Povo (TN), Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Farid","family":"Melgani","sequence":"additional","affiliation":[{"name":"Department of Information Engineering and Computer Science, University of Trento, Via Sommarive, 9, I-38123 Povo (TN), Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pietro","family":"Beraldini","sequence":"additional","affiliation":[{"name":"Athena Srl., Via Nenni, 7, I-37024 Negrar (VR), Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2019,5,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1635","DOI":"10.1109\/TGRS.2013.2253108","article-title":"Automatic Car Counting Method for Unmanned Aerial Vehicle Images","volume":"52","author":"Moranduzzo","year":"2014","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"6356","DOI":"10.1109\/TGRS.2013.2296351","article-title":"Detecting Cars in UAV Images with a Catalog-Based Approach","volume":"52","author":"Moranduzzo","year":"2014","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/BF00994018","article-title":"Support-vector networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach. Learn."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., and Li, L. (2009, January 20\u201325). ImageNet: A large-scale hierarchical image database. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Bejiga, M.B., Zeggada, A., Nouffidj, A., and Melgani, F. (2017). A Convolutional Neural Network Approach for Assisting Avalanche Search and Rescue Operations with UAV Imagery. Remote Sens., 9.","DOI":"10.3390\/rs9020100"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"6712","DOI":"10.1109\/TGRS.2018.2841823","article-title":"Exploring Hierarchical Convolutional Features for Hyperspectral Image Classification","volume":"56","author":"Cheng","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Zhou, P., Han, J., Cheng, G., and Zhang, B. (2019). Learning Compact and Discriminative Stacked Autoencoder for Hyperspectral Image Classification. IEEE Trans. Geosci. Remote Sens.","DOI":"10.1109\/TGRS.2019.2893180"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2811","DOI":"10.1109\/TGRS.2017.2783902","article-title":"When Deep Learning Meets Metric Learning: Remote Sensing Image Scene Classification via Learning Discriminative CNNs","volume":"56","author":"Cheng","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1109\/MGRS.2016.2548504","article-title":"Domain Adaptation for the Classification of Remote Sensing Data: An Overview of Recent Advances","volume":"4","author":"Tuia","year":"2016","journal-title":"IEEE Geosci. Remote Sens. Mag."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"867","DOI":"10.1109\/JSTARS.2012.2222356","article-title":"Gaussian Process Retrieval of Chlorophyll Content from Imaging Spectroscopy Data","volume":"6","author":"Verrelst","year":"2013","journal-title":"IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Ballanti, L., Blesius, L., Hines, E., and Kruse, B. (2016). Tree Species Classification Using Hyperspectral Imagery: A Comparison of Two Classifiers. Remote Sens., 8.","DOI":"10.3390\/rs8060445"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Persello, C., and Bruzzone, L. (2009, January 12\u201317). A novel approach to the selection of spatially invariant features for classification of hyperspectral images. Proceedings of the 2009 IEEE International Geoscience and Remote Sensing Symposium, Cape Town, South Africa.","DOI":"10.1109\/IGARSS.2009.5418001"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"2615","DOI":"10.1109\/TGRS.2015.2503885","article-title":"Kernel-Based Domain-Invariant Feature Selection in Hyperspectral Images for Transfer Learning","volume":"54","author":"Persello","year":"2016","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Izquierdo-Verdiguier, E., Laparra, V., G\u00f3mez-Chova, L., and Camps-Valls, G. (2012, January 22\u201327). Including invariances in SVM remote sensing image classification. Proceedings of the 2012 IEEE International Geoscience and Remote Sensing Symposium, Munich, Germany.","DOI":"10.1109\/IGARSS.2012.6351931"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1243","DOI":"10.1109\/TGRS.2007.912445","article-title":"Multidimensional Probability Density Function Matching for Preprocessing of Multitemporal Remote Sensing Images","volume":"46","author":"Inamdar","year":"2008","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"3550","DOI":"10.1109\/TGRS.2014.2377785","article-title":"Semisupervised Transfer Component Analysis for Domain Adaptation in Remote Sensing Image Classification","volume":"53","author":"Matasci","year":"2015","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1109\/TNN.2010.2091281","article-title":"Domain Adaptation via Transfer Component Analysis","volume":"22","author":"Pan","year":"2011","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1016\/j.isprsjprs.2015.02.005","article-title":"Spectral alignment of multi-temporal cross-sensor images with automated kernel canonical correlation analysis","volume":"107","author":"Volpi","year":"2015","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"2662","DOI":"10.1109\/TGRS.2011.2105490","article-title":"Spatially Adaptive Classification of Land Cover with Remote Sensing Data","volume":"49","author":"Jun","year":"2011","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Gonzalez, D.M., Camps-Valls, G., and Tuia, D. (2015, January 26\u201331). Weakly supervised alignment of multisensor images. Proceedings of the 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Milan, Italy.","DOI":"10.1109\/IGARSS.2015.7326341"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"7708","DOI":"10.1109\/TGRS.2014.2317499","article-title":"Semisupervised Manifold Alignment of Multimodal Remote Sensing Images","volume":"52","author":"Tuia","year":"2014","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1109\/TGRS.2015.2449736","article-title":"Spectral and Spatial Proximity-Based Manifold Alignment for Multitemporal Hyperspectral Image Classification","volume":"54","author":"Yang","year":"2016","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"543","DOI":"10.1109\/JSTARS.2015.2449738","article-title":"Domain Adaptation with Preservation of Manifold Geometry for Hyperspectral Image Classification","volume":"9","author":"Yang","year":"2016","journal-title":"IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1109\/TGRS.2012.2200045","article-title":"Graph Matching for Adaptation in Remote Sensing","volume":"51","author":"Tuia","year":"2013","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_25","first-page":"354","article-title":"Three-Layer Convex Network for Domain Adaptation in Multitemporal VHR Images","volume":"13","author":"Othman","year":"2016","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"527","DOI":"10.1109\/LGRS.2014.2349538","article-title":"Fusion of Extreme Learning Machine and Graph-Based Optimization Methods for Active Classification of Remote Sensing Images","volume":"12","author":"Bencherif","year":"2015","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"2901","DOI":"10.1109\/JSTARS.2015.2500961","article-title":"Transfer Sparse Subspace Analysis for Unsupervised Cross-View Scene Model Adaptation","volume":"9","author":"Sun","year":"2016","journal-title":"IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"3408","DOI":"10.1109\/TGRS.2006.878442","article-title":"Exploiting Class Hierarchies for Knowledge Transfer in Hyperspectral Data","volume":"44","author":"Rajan","year":"2006","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"770","DOI":"10.1109\/TPAMI.2009.57","article-title":"Domain Adaptation Problems: A DASVM Classification Technique and a Circular Validation Strategy","volume":"32","author":"Bruzzone","year":"2010","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1224","DOI":"10.1109\/LGRS.2012.2236818","article-title":"Learn Multiple-Kernel SVMs for Domain Adaptation in Hyperspectral Data","volume":"10","author":"Sun","year":"2013","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1109\/LGRS.2008.916070","article-title":"Semisupervised Image Classification with Laplacian Support Vector Machines","volume":"5","author":"Calpe","year":"2008","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1870","DOI":"10.1109\/TGRS.2007.894550","article-title":"Semisupervised Classification of Hyperspectral Images by SVMs Optimized in the Primal","volume":"45","author":"Chi","year":"2007","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"3363","DOI":"10.1109\/TGRS.2006.877950","article-title":"A Novel Transductive SVM for Semisupervised Classification of Remote-Sensing Images","volume":"44","author":"Bruzzone","year":"2006","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1109\/TGRS.2012.2200043","article-title":"Multitask Remote Sensing Data Classification","volume":"51","year":"2013","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1231","DOI":"10.1109\/TGRS.2007.910220","article-title":"An Active Learning Approach to Hyperspectral Data Classification","volume":"46","author":"Rajan","year":"2008","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"2218","DOI":"10.1109\/TGRS.2008.2010404","article-title":"Active Learning Methods for Remote Sensing Image Classification","volume":"47","author":"Tuia","year":"2009","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"2232","DOI":"10.1016\/j.rse.2011.04.022","article-title":"Using active learning to adapt remote sensing image classifiers","volume":"115","author":"Tuia","year":"2011","journal-title":"Remote Sens. Environ."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"1335","DOI":"10.1109\/JSTARS.2012.2202881","article-title":"SVM-Based Boosting of Active Learning Strategies for Efficient Domain Adaptation","volume":"5","author":"Matasci","year":"2012","journal-title":"IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"4468","DOI":"10.1109\/TGRS.2012.2192740","article-title":"Active Learning for Domain Adaptation in the Supervised Classification of Remote Sensing Images","volume":"50","author":"Persello","year":"2012","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1109\/LGRS.2013.2255258","article-title":"Large-Scale Image Classification Using Active Learning","volume":"11","author":"Alajlan","year":"2014","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"6652","DOI":"10.1109\/TGRS.2014.2300189","article-title":"Cost-Sensitive Active Learning with Lookahead: Optimizing Field Surveys for Remote Sensing Data Classification","volume":"52","author":"Persello","year":"2014","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1272","DOI":"10.1109\/TGRS.2013.2249522","article-title":"Definition of Effective Training Sets for Supervised Classification of Remote Sensing Images by a Novel Cost-Sensitive Active Learning Method","volume":"52","author":"Demir","year":"2014","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"2492","DOI":"10.1109\/TGRS.2013.2262052","article-title":"Active Learning in the Spatial Domain for Remote Sensing Image Classification","volume":"52","author":"Stumpf","year":"2014","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Csurka, G. (2017). Domain-Adversarial Training of Neural Networks. Domain Adaptation in Computer Vision Applications, Springer International Publishing.","DOI":"10.1007\/978-3-319-58347-1"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"4198","DOI":"10.1109\/JSTARS.2017.2711360","article-title":"Domain Adaptation Using Representation Learning for the Classification of Remote Sensing Images","volume":"10","author":"Elshamli","year":"2017","journal-title":"IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens."},{"key":"ref_46","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A Method for Stochastic Optimization. arXiv."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Vincent, P., Larochelle, H., Bengio, Y., and Manzagol, P.-A. (2008, January 5\u20139). Extracting and composing robust features with denoising autoencoders. Proceedings of the 25th International Conference on Machine Learning, Helsinki, Finland.","DOI":"10.1145\/1390156.1390294"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/11\/10\/1153\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T12:51:54Z","timestamp":1760187114000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/11\/10\/1153"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5,14]]},"references-count":47,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2019,5]]}},"alternative-id":["rs11101153"],"URL":"https:\/\/doi.org\/10.3390\/rs11101153","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,5,14]]}}}