{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T01:11:55Z","timestamp":1768353115744,"version":"3.49.0"},"reference-count":73,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2021,6,24]],"date-time":"2021-06-24T00:00:00Z","timestamp":1624492800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000003","name":"ArcticNet","doi-asserted-by":"publisher","award":["-"],"award-info":[{"award-number":["-"]}],"id":[{"id":"10.13039\/501100000003","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Sea ice observations through satellite imaging have led to advancements in environmental research, ship navigation, and ice hazard forecasting in cold regions. Machine learning and, recently, deep learning techniques are being explored by various researchers to process vast amounts of Synthetic Aperture Radar (SAR) data for detecting potential hazards in navigational routes. Detection of hazards such as sea ice floes in Marginal Ice Zones (MIZs) is quite challenging as the floes are often embedded in a multiscale ice cover composed of ice filaments and eddies in addition to floes. This study proposes a segmentation model tailored for detecting ice floes in SAR images. The model exploits the advantages of both convolutional neural networks and convolutional conditional random field (Conv-CRF) in a combined manner. The residual UNET (RES-UNET) computes expressive features to generate coarse segmentation maps while the Conv-CRF exploits the spatial co-occurrence pairwise potentials along with the RES-UNET unary\/segmentation maps to generate final predictions. The whole pipeline is trained end-to-end using a dual loss function. This dual loss function is composed of a weighted average of binary cross entropy and soft dice loss. The comparison of experimental results with the conventional segmentation networks such as UNET, DeepLabV3, and FCN-8 demonstrates the effectiveness of the proposed architecture.<\/jats:p>","DOI":"10.3390\/rs13132460","type":"journal-article","created":{"date-parts":[[2021,6,24]],"date-time":"2021-06-24T04:24:36Z","timestamp":1624508676000},"page":"2460","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":33,"title":["RUF: Effective Sea Ice Floe Segmentation Using End-to-End RES-UNET-CRF with Dual Loss"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4804-2934","authenticated-orcid":false,"given":"Anmol Sharan","family":"Nagi","sequence":"first","affiliation":[{"name":"Department of Systems Design Engineering, University of Waterloo, Waterloo, ON N2L G31, Canada"}]},{"given":"Devinder","family":"Kumar","sequence":"additional","affiliation":[{"name":"School of Medicine, Stanford University, Stanford, CA 94305, USA"}]},{"given":"Daniel","family":"Sola","sequence":"additional","affiliation":[{"name":"Department of Systems Design Engineering, University of Waterloo, Waterloo, ON N2L G31, Canada"}]},{"given":"K. Andrea","family":"Scott","sequence":"additional","affiliation":[{"name":"Department of Systems Design Engineering, University of Waterloo, Waterloo, ON N2L G31, Canada"}]}],"member":"1968","published-online":{"date-parts":[[2021,6,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1038\/nclimate2848","article-title":"Mapping the future expansion of Arctic open water","volume":"6","author":"Barnhart","year":"2016","journal-title":"Nat. Clim. Chang."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1525\/elementa.281","article-title":"Climate change and sea ice: Shipping in Hudson Bay, Hudson Strait, and Foxe Basin (1980\u20132016)","volume":"6","author":"Andrews","year":"2018","journal-title":"Elem. Sci. Anth."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2370","DOI":"10.1002\/2017GL076587","article-title":"Increasing mobility of high Arctic sea ice increases marine hazards off the east coast of Newfoundland","volume":"45","author":"Barber","year":"2018","journal-title":"Geophys. Res. Lett."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"448","DOI":"10.5589\/m04-011","article-title":"Potential of RADARSAT-2 data for operational sea ice monitoring","volume":"30","author":"Scheuchl","year":"2004","journal-title":"Can. J. Remote Sens."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"935","DOI":"10.1134\/S0001433815090182","article-title":"Satellite monitoring of ice features to ensure safety of offshore operations in the Arctic seas","volume":"51","author":"Smirnov","year":"2015","journal-title":"Izv. Atmos. Ocean. Phys."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"933","DOI":"10.1016\/j.dsr2.2007.12.016","article-title":"Observed changes in sea-ice floe size distribution during early summer in the western Weddell Sea","volume":"55","author":"Steer","year":"2008","journal-title":"Deep Sea Res. Part II Top. Stud. Oceanogr."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1182","DOI":"10.1016\/j.dsr2.2010.10.034","article-title":"Size distribution and shape properties of relatively small sea-ice floes in the Antarctic marginal ice zone in late winter","volume":"58","author":"Toyota","year":"2011","journal-title":"Deep Sea Res. Part II Top. Stud. Oceanogr."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1017","DOI":"10.1029\/1999JC000110","article-title":"The effect of a storm on the 1992 summer sea ice cover of the Beaufort, Chukchi, and East Siberian Seas","volume":"106","author":"Holt","year":"2001","journal-title":"J. Geophys. Res. Ocean."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1525\/elementa.154","article-title":"A practical algorithm for the retrieval of floe size distribution of Arctic sea ice from high-resolution satellite Synthetic Aperture Radar imagery","volume":"5","author":"Hwang","year":"2017","journal-title":"Elem. Sci. Anth."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1109\/TGRS.2003.817218","article-title":"Comparing cooccurrence probabilities and Markov random fields for texture analysis of SAR sea ice imagery","volume":"42","author":"Clausi","year":"2004","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"2451","DOI":"10.1109\/JSTARS.2016.2551318","article-title":"Antarctic Sea-Ice Classification Based on Conditional Random Fields From RADARSAT-2 Dual-Polarization Satellite Images","volume":"9","author":"Zhu","year":"2016","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"4735","DOI":"10.1109\/TGRS.2019.2892723","article-title":"Estimating Sea Ice Concentration From SAR: Training Convolutional Neural Networks With Passive Microwave Data","volume":"57","author":"Cooke","year":"2019","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1016\/S0165-232X(01)00057-X","article-title":"A systematic method of obtaining ice concentration measurements from ship-based observations","volume":"34","author":"Hall","year":"2002","journal-title":"Cold Reg. Sci. Technol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"2771","DOI":"10.1109\/TGRS.2010.2042962","article-title":"A method of obtaining ice concentration and floe size from shipboard oblique sea ice images","volume":"48","author":"Lu","year":"2010","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"898","DOI":"10.1109\/JOE.2019.2899473","article-title":"Ice condition assessment using onboard accelerometers and statistical change detection","volume":"45","author":"Heyn","year":"2019","journal-title":"IEEE J. Ocean. Eng."},{"key":"ref_16","first-page":"V008T07A012","article-title":"A system for automated vision-based sea-ice concentration detection and floe-size distribution indication from an icebreaker","volume":"Volume 57762","author":"Heyn","year":"2017","journal-title":"Proceedings of the International Conference on Offshore Mechanics and Arctic Engineering"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"931","DOI":"10.1080\/17538947.2017.1421720","article-title":"2014 summer Arctic sea ice thickness and concentration from shipborne observations","volume":"12","author":"Wang","year":"2019","journal-title":"Int. J. Digit. Earth"},{"key":"ref_18","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_19","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_20","unstructured":"Teichmann, M.T.T., and Cipolla, R. (2018). Convolutional CRFs for Semantic Segmentation. arXiv."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"053024","DOI":"10.1117\/1.JEI.28.5.053024","article-title":"U-net like deep autoencoders for deblurring atmospheric turbulence","volume":"28","author":"Chen","year":"2019","journal-title":"J. Electron. Imaging"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Hu, X., Naiel, M.A., Wong, A., Lamm, M., and Fieguth, P. (2019, January 16\u201317). RUNet: A Robust UNet Architecture for Image Super-Resolution. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Long Beach, CA, USA.","DOI":"10.1109\/CVPRW.2019.00073"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"3194","DOI":"10.1002\/mp.13577","article-title":"Ultrasound prostate segmentation based on multidirectional deeply supervised V-Net","volume":"46","author":"Lei","year":"2019","journal-title":"Med. Phys."},{"key":"ref_24","unstructured":"Haugen, J., Imsland, L., L\u00f8set, S., and Skjetne, R. (2011, January 19\u201324). Ice observer system for ice management operations. Proceedings of the Twenty-First International Offshore and Polar Engineering Conference, Maui, HI, USA."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"5529","DOI":"10.1109\/TGRS.2013.2290231","article-title":"Automated ice\u2013water classification using dual polarization SAR satellite imagery","volume":"52","author":"Leigh","year":"2013","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Hoekstra, M., Jiang, M., Clausi, D.A., and Duguay, C. (2020). Lake Ice-Water Classification of RADARSAT-2 Images by Integrating IRGS Segmentation with Pixel-Based Random Forest Labeling. Remote Sens., 12.","DOI":"10.3390\/rs12091425"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"111948","DOI":"10.1016\/j.rse.2020.111948","article-title":"Discrimination of open water from sea ice in the Labrador Sea using quad-polarized synthetic aperture radar","volume":"247","author":"Xie","year":"2020","journal-title":"Remote Sens. Environ."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"4524","DOI":"10.1109\/TGRS.2016.2543660","article-title":"Sea ice concentration estimation during melt from dual-pol SAR scenes using deep convolutional neural networks: A case study","volume":"54","author":"Wang","year":"2016","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1289","DOI":"10.5194\/tc-14-1289-2020","article-title":"Accuracy and inter-analyst agreement of visually estimated sea ice concentrations in Canadian Ice Service ice charts using single-polarization RADARSAT-2","volume":"14","author":"Cheng","year":"2020","journal-title":"Cryosphere"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"2871","DOI":"10.1109\/TGRS.2017.2655567","article-title":"Baltic sea ice concentration estimation using SENTINEL-1 SAR and AMSR2 microwave radiometer data","volume":"55","author":"Karvonen","year":"2017","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_31","unstructured":"Shi, L., Karvonen, J., Cheng, B., Vihma, T., Lin, M., Liu, Y., Wang, Q., and Jia, Y. (2014, January 13\u201318). Sea ice thickness retrieval from SAR imagery over Bohai sea. Proceedings of the 2014 IEEE Geoscience and Remote Sensing Symposium, Quebec City, QC, Canada."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Karvonen, J., Shi, L., Cheng, B., Simil\u00e4, M., M\u00e4kynen, M., and Vihma, T. (2017). Bohai Sea ice parameter estimation based on thermodynamic ice model and Earth observation data. Remote Sens., 9.","DOI":"10.3390\/rs9030234"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"2587","DOI":"10.1109\/TGRS.2012.2212445","article-title":"Classification of sea ice types in ENVISAT synthetic aperture radar images","volume":"51","author":"Zakhvatkina","year":"2012","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_34","first-page":"1","article-title":"Classification of Sea Ice Types in Sentinel-1 SAR images","volume":"2019","author":"Park","year":"2019","journal-title":"Cryosphere Discuss."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Nagi, A.S., Minhas, M.S., Xu, L., and Scott, K.A. (October, January 26). A Multi-Scale Technique to Detect Marginal Ice Zones Using Convolutional Neural Networks. Proceedings of the IGARSS 2020-2020 IEEE International Geoscience and Remote Sensing Symposium, Waikoloa, HI, USA.","DOI":"10.1109\/IGARSS39084.2020.9324172"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Sola, D., Nagi, A.S., and Scott, K.A. (October, January 26). Identifying Sea Ice Ridging in SAR Imagery Using Convolutional Neural Networks. Proceedings of the IGARSS 2020-2020 IEEE International Geoscience and Remote Sensing Symposium, Waikoloa, HI, USA.","DOI":"10.1109\/IGARSS39084.2020.9323949"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Lang, F., Yang, J., Yan, S., and Qin, F. (2018). Superpixel segmentation of polarimetric synthetic aperture radar (sar) images based on generalized mean shift. Remote Sens., 10.","DOI":"10.3390\/rs10101592"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Zhang, W., Xiang, D., and Su, Y. (2020). Fast Multiscale Superpixel Segmentation for SAR Imagery. IEEE Geosci. Remote. Sens. Lett., 1\u20135.","DOI":"10.1109\/LGRS.2020.3022478"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1016\/j.eswa.2017.04.018","article-title":"River channel segmentation in polarimetric SAR images: Watershed transform combined with average contrast maximisation","volume":"82","author":"Ciecholewski","year":"2017","journal-title":"Expert Syst. Appl."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Ijitona, T.B., Ren, J., and Hwang, P.B. (2014, January 11\u201313). SAR sea ice image segmentation using watershed with intensity-based region merging. Proceedings of the 2014 IEEE International Conference on Computer and Information Technology, Xi\u2019an, China.","DOI":"10.1109\/CIT.2014.19"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1171","DOI":"10.1109\/LGRS.2017.2702062","article-title":"A median regularized level set for hierarchical segmentation of SAR images","volume":"14","author":"Braga","year":"2017","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"4565","DOI":"10.1109\/JSTARS.2017.2716620","article-title":"Level set segmentation algorithm for high-resolution polarimetric SAR images based on a heterogeneous clutter model","volume":"10","author":"Jin","year":"2017","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Zhang, T., Zhang, X., Shi, J., and Wei, S. (2019). Depthwise separable convolution neural network for high-speed SAR ship detection. Remote Sens., 11.","DOI":"10.3390\/rs11212483"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Zhang, T., and Zhang, X. (2019). High-speed ship detection in SAR images based on a grid convolutional neural network. Remote Sens., 11.","DOI":"10.3390\/rs11101206"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Zhang, T., Zhang, X., Ke, X., Zhan, X., Shi, J., Wei, S., Pan, D., Li, J., Su, H., and Zhou, Y. (2020). LS-SSDD-v1.0: A Deep Learning Dataset Dedicated to Small Ship Detection from Large-Scale Sentinel-1 SAR Images. Remote Sens., 12.","DOI":"10.3390\/rs12182997"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1109\/36.368223","article-title":"A comprehensive, automated approach to determining sea ice thickness from SAR data","volume":"33","author":"Haverkamp","year":"1995","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_47","unstructured":"Tsatsoulis, C., and Kwok, R. (2012). Analysis of SAR Data of the Polar Oceans: Recent Advances, Springer Science & Business Media."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"545","DOI":"10.1109\/TIP.2010.2066982","article-title":"Multiregion image segmentation by parametric kernel graph cuts","volume":"20","author":"Salah","year":"2010","journal-title":"IEEE Trans. Image Process."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1006\/gmip.1996.0002","article-title":"A hierarchical Markov random field model and multitemperature annealing for parallel image classification","volume":"58","author":"Kato","year":"1996","journal-title":"Graph. Model. Image Process."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Ren, J., Hwang, B., Murray, P., Sakhalkar, S., and McCormack, S. (2015, January 26\u201331). Effective SAR sea ice image segmentation and touch floe separation using a combined multi-stage approach. Proceedings of the 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Milan, Italy.","DOI":"10.1109\/IGARSS.2015.7325947"},{"key":"ref_51","unstructured":"Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012, January 3\u20136). Imagenet classification with deep convolutional neural networks. Proceedings of the Advances in Neural Information Processing Systems, Lake Tahoe, NV, USA."},{"key":"ref_52","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_53","unstructured":"Iandola, F., Moskewicz, M., Karayev, S., Girshick, R., Darrell, T., and Keutzer, K. (2014). Densenet: Implementing efficient convnet descriptor pyramids. arXiv."},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., and Darrell, T. (2015, January 7\u201312). Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1109\/TPAMI.2015.2437384","article-title":"Region-based convolutional networks for accurate object detection and segmentation","volume":"38","author":"Girshick","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_56","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_57","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","article-title":"Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs","volume":"40","author":"Chen","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_58","doi-asserted-by":"crossref","unstructured":"Wang, P., Chen, P., Yuan, Y., Liu, D., Huang, Z., Hou, X., and Cottrell, G. (2018, January 12\u201315). Understanding convolution for semantic segmentation. Proceedings of the 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), Lake Tahoe, NV, USA.","DOI":"10.1109\/WACV.2018.00163"},{"key":"ref_59","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., and Adam, H. (2017). Rethinking atrous convolution for semantic image segmentation. arXiv."},{"key":"ref_60","doi-asserted-by":"crossref","first-page":"7570","DOI":"10.1109\/TGRS.2020.2981082","article-title":"River ice segmentation with deep learning","volume":"58","author":"Singh","year":"2020","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_61","doi-asserted-by":"crossref","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","article-title":"Segnet: A deep convolutional encoder-decoder architecture for image segmentation","volume":"39","author":"Badrinarayanan","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_62","doi-asserted-by":"crossref","unstructured":"Zhang, X., Jin, J., Lan, Z., Li, C., Fan, M., Wang, Y., Yu, X., and Zhang, Y. (2020). ICENET: A Semantic Segmentation Deep Network for River Ice by Fusing Positional and Channel-Wise Attentive Features. Remote Sens., 12.","DOI":"10.3390\/rs12020221"},{"key":"ref_63","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1175\/MWR-D-16-0110.1","article-title":"Collecting empirically derived SAR characteristic values over one year of sea ice environments for use in data assimilation","volume":"145","author":"Pogson","year":"2017","journal-title":"Mon. Weather Rev."},{"key":"ref_64","doi-asserted-by":"crossref","unstructured":"Clausi, D., Qin, A., Chowdhury, M., Yu, P., and Maillard, P. (2008, January 7). MAGIC: Map-guided ice classification system for operational analysis. Proceedings of the 2008 IAPR Workshop on Pattern Recognition in Remote Sensing (PRRS 2008), Tampa, FL, USA.","DOI":"10.1109\/PRRS.2008.4783172"},{"key":"ref_65","unstructured":"Rolnick, D., and Tegmark, M. (2017). The power of deeper networks for expressing natural functions. arXiv."},{"key":"ref_66","unstructured":"Mhaskar, H., Liao, Q., and Poggio, T. (2016). Learning functions: When is deep better than shallow. arXiv."},{"key":"ref_67","doi-asserted-by":"crossref","unstructured":"Zheng, S., Jayasumana, S., Romera-Paredes, B., Vineet, V., Su, Z., Du, D., Huang, C., and Torr, P.H. (2015, January 11\u201318). Conditional random fields as recurrent neural networks. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.179"},{"key":"ref_68","unstructured":"Ma, Y.-D., Liu, Q., and Qian, A.B. (2004, January 20\u201322). Automated image segmentation using improved PCNN model based on cross-entropy. Proceedings of the 2004 International Symposium on Intelligent Multimedia, Video and Speech Processing, Hong Kong, China."},{"key":"ref_69","doi-asserted-by":"crossref","unstructured":"Sudre, C.H., Li, W., Vercauteren, T., Ourselin, S., and Cardoso, M.J. (2017). Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, Springer.","DOI":"10.1007\/978-3-319-67558-9_28"},{"key":"ref_70","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2015, January 11\u201318). Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref_71","unstructured":"Kr\u00e4henb\u00fchl, P., and Koltun, V. (2012). Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials. arXiv."},{"key":"ref_72","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_73","unstructured":"Tan, M., and Le, Q. (2019, January 10\u201315). Efficientnet: Rethinking model scaling for convolutional neural networks. Proceedings of the International Conference on Machine Learning, PMLR, Long Beach, CA, USA."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/13\/2460\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:22:42Z","timestamp":1760163762000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/13\/2460"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,24]]},"references-count":73,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2021,7]]}},"alternative-id":["rs13132460"],"URL":"https:\/\/doi.org\/10.3390\/rs13132460","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6,24]]}}}