{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T01:57:48Z","timestamp":1760234268784,"version":"build-2065373602"},"reference-count":25,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T00:00:00Z","timestamp":1619481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"the National Key Research and Development Program of China","award":["2017YFB0504203"],"award-info":[{"award-number":["2017YFB0504203"]}]},{"name":"the Natural Science Foundation of China project","award":["41601212, 41801360, 41771403, 41801358"],"award-info":[{"award-number":["41601212, 41801360, 41771403, 41801358"]}]},{"name":"the Fundamental Research Foundation of Shenzhen Technology and Innovation Council","award":["KCXFZ202002011006298"],"award-info":[{"award-number":["KCXFZ202002011006298"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>The deep-learning-network performance depends on the accuracy of the training samples. The training samples are commonly labeled by human visual investigation or inherited from historical land-cover or land-use maps, which usually contain label noise, depending on subjective knowledge and the time of the historical map. Helping the network to distinguish noisy labels during the training process is a prerequisite for applying the model for training across time and locations. This study proposes an antinoise framework, the Weight Loss Network (WLN), to achieve this goal. The WLN contains three main parts: (1) the segmentation subnetwork, which any state-of-the-art segmentation network can replace; (2) the attention subnetwork (\u03bb); and (3) the class-balance coefficient (\u03b1). Four types of label noise (an insufficient label, redundant label, missing label and incorrect label) were simulated by dilate and erode processing to test the network\u2019s antinoise ability. The segmentation task was set to extract buildings from the Inria Aerial Image Labeling Dataset, which includes Austin, Chicago, Kitsap County, Western Tyrol and Vienna. The network\u2019s performance was evaluated by comparing it with the original U-Net model by adding noisy training samples with different noise rates and noise levels. The result shows that the proposed antinoise framework (WLN) can maintain high accuracy, while the accuracy of the U-Net model dropped. Specifically, after adding 50% of dilated-label samples at noise level 3, the U-Net model\u2019s accuracy dropped by 12.7% for OA, 20.7% for the Mean Intersection over Union (MIOU) and 13.8% for Kappa scores. By contrast, the accuracy of the WLN dropped by 0.2% for OA, 0.3% for the MIOU and 0.8% for Kappa scores. For eroded-label samples at the same level, the accuracy of the U-Net model dropped by 8.4% for OA, 24.2% for the MIOU and 43.3% for Kappa scores, while the accuracy of the WLN dropped by 4.5% for OA, 4.7% for the MIOU and 0.5% for Kappa scores. This result shows that the antinoise framework proposed in this paper can help current segmentation models to avoid the impact of noisy training labels and has the potential to be trained by a larger remote sensing image set regardless of the inner label error.<\/jats:p>","DOI":"10.3390\/rs13091689","type":"journal-article","created":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T21:18:20Z","timestamp":1619558300000},"page":"1689","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Deep Learning Network Intensification for Preventing Noisy-Labeled Samples for Remote Sensing Classification"],"prefix":"10.3390","volume":"13","author":[{"given":"Chuang","family":"Lin","sequence":"first","affiliation":[{"name":"Center for Geo-Spatial Information, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China"},{"name":"University of Chinese Academy of Sciences, Beijing 101407, China"}]},{"given":"Shanxin","family":"Guo","sequence":"additional","affiliation":[{"name":"Center for Geo-Spatial Information, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China"},{"name":"Shenzhen Engineering Laboratory of Ocean Environmental Big Data Analysis and Application, Shenzhen 518055, China"}]},{"given":"Jinsong","family":"Chen","sequence":"additional","affiliation":[{"name":"Center for Geo-Spatial Information, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China"},{"name":"Shenzhen Engineering Laboratory of Ocean Environmental Big Data Analysis and Application, Shenzhen 518055, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4575-0836","authenticated-orcid":false,"given":"Luyi","family":"Sun","sequence":"additional","affiliation":[{"name":"Center for Geo-Spatial Information, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China"},{"name":"Shenzhen Engineering Laboratory of Ocean Environmental Big Data Analysis and Application, Shenzhen 518055, China"}]},{"given":"Xiaorou","family":"Zheng","sequence":"additional","affiliation":[{"name":"Center for Geo-Spatial Information, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China"},{"name":"University of Chinese Academy of Sciences, Beijing 101407, China"}]},{"given":"Yan","family":"Yang","sequence":"additional","affiliation":[{"name":"Big Data Center of Geospatial and Natural Resources of Qinghai Province, Xining 810000, China"}]},{"given":"Yingfei","family":"Xiong","sequence":"additional","affiliation":[{"name":"Center for Geo-Spatial Information, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China"},{"name":"University of Chinese Academy of Sciences, Beijing 101407, China"}]}],"member":"1968","published-online":{"date-parts":[[2021,4,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"851","DOI":"10.1109\/TGRS.2018.2861992","article-title":"Hyperspectral image classification in the presence of noisy labels","volume":"57","author":"Jiang","year":"2019","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_2","first-page":"1297","article-title":"Learning from crowds","volume":"11","author":"Raykar","year":"2010","journal-title":"J. Mach. Learn. Res."},{"doi-asserted-by":"crossref","unstructured":"Huang, J., Qu, L., Jia, R., and Zhao, B. (2019, January 27\u201328). O2U-Net: A simple noisy label detection approach for deep neural networks. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Korea.","key":"ref_3","DOI":"10.1109\/ICCV.2019.00342"},{"unstructured":"Song, H., Kim, M., Park, D., and Lee, J.G. (2020). Two-phase learning for overcoming noisy labels. arXiv.","key":"ref_4"},{"unstructured":"Wu, P., Zheng, S., Goswami, M., Metaxas, D., and Chen, C. (2020). A topological filter for learning with label noise. arXiv.","key":"ref_5"},{"unstructured":"Li, J., Socher, R., and Hoi, S.C.H. (2020). Dividemix: Learning with noisy labels as semi-supervised learning. arXiv.","key":"ref_6"},{"unstructured":"Zhou, T., Wang, S., and Bilmes, J. (2021, January 28\u201329). Robust Curriculum Learning: From clean label detection to noisy label self-correction. Proceedings of the International Conference on Learning Representations, Lisbon, Portugal.","key":"ref_7"},{"unstructured":"Han, B., Yao, Q., Yu, X., Niu, G., Xu, M., Hu, W., Tsang, I.W., and Sugiyama, M. (2018). Co-teaching: Robust training of deep neural networks with extremely noisy labels. arXiv.","key":"ref_8"},{"doi-asserted-by":"crossref","unstructured":"Chen, X., and Gupta, A. (2015, January 7\u201313). Webly supervised learning of convolutional networks. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","key":"ref_9","DOI":"10.1109\/ICCV.2015.168"},{"unstructured":"Sukhbaatar, S., Bruna, J., Paluri, M., Bourdev, L., and Fergus, R. (2015, January 7\u20139). Training convolutional networks with noisy labels. Proceedings of the 3rd International Conference on Learning Representations, San Diego, CA, USA.","key":"ref_10"},{"unstructured":"Xiao, T., Xia, T., Yang, Y., Huang, C., and Wang, X. (2015, January 7\u201312). Learning from massive noisy labeled data for image classification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","key":"ref_11"},{"unstructured":"Yao, Y., Liu, T., Han, B., Gong, M., Deng, J., Niu, G., and Sugiyama, M. (2020). Dual T: Reducing estimation error for transition matrix in label-noise learning. arXiv.","key":"ref_12"},{"doi-asserted-by":"crossref","unstructured":"Ghosh, A., Kumar, H., and Sastry, P.S. (2017, January 4\u20139). Robust loss functions under label noise for deep neural networks. Proceedings of the 31st AAAI Conference on Artificial Intelligence, San Francisco, CA, USA.","key":"ref_13","DOI":"10.1609\/aaai.v31i1.10894"},{"unstructured":"Zhang, Z., and Sabuncu, M.R. (2018). Generalized cross entropy loss for training deep neural networks with noisy labels. arXiv.","key":"ref_14"},{"doi-asserted-by":"crossref","unstructured":"Wang, Y., Ma, X., Chen, Z., Luo, Y., Yi, J., and Bailey, J. (2019, January 27\u201328). Symmetric cross entropy for robust learning with noisy labels. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Korea.","key":"ref_15","DOI":"10.1109\/ICCV.2019.00041"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1109\/TPAMI.2015.2456899","article-title":"Classification with Noisy Labels by Importance Reweighting","volume":"38","author":"Liu","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"unstructured":"Shu, J., Xie, Q., Yi, L., Zhao, Q., Xu, Z., Zhou, S., and Meng, D. (2019). Meta-weight-net: Learning an explicit mapping for sample weighting. arXiv.","key":"ref_17"},{"doi-asserted-by":"crossref","unstructured":"Jenni, S., and Favaro, P. (2018, January 8\u201314). Deep bilevel learning. Proceedings of the European Conference on Computer Vision, Munich, Germany.","key":"ref_18","DOI":"10.1007\/978-3-030-01249-6_38"},{"unstructured":"Ren, M., Zeng, W., Yang, B., and Urtasun, R. (2018, January 10\u201315). Learning to reweight examples for robust deep learning. Proceedings of the 35th International Conference on Machine Learning, Stockholm, Sweden.","key":"ref_19"},{"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. In Proceedings of the IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Fort Worth, TX, USA.","key":"ref_20","DOI":"10.1109\/IGARSS.2017.8127684"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"845","DOI":"10.1109\/TNNLS.2013.2292894","article-title":"Classification in the presence of label noise: A survey","volume":"25","author":"Verleysen","year":"2014","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_22","first-page":"6000","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"doi-asserted-by":"crossref","unstructured":"Fu, J., Liu, J., Tian, H., Li, Y., Bao, Y., Fang, Z., and Lu, H. (2019, January 20). Dual attention network for scene segmentation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","key":"ref_23","DOI":"10.1109\/CVPR.2019.00326"},{"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.","key":"ref_24","DOI":"10.1007\/978-3-319-24574-4_28"},{"doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Albanie, S., Sun, G., and Wu, E. (2020). Squeeze-and-Excitation Networks. arXiv.","key":"ref_25","DOI":"10.1109\/TPAMI.2019.2913372"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/9\/1689\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T05:53:25Z","timestamp":1760162005000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/9\/1689"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,27]]},"references-count":25,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2021,5]]}},"alternative-id":["rs13091689"],"URL":"https:\/\/doi.org\/10.3390\/rs13091689","relation":{},"ISSN":["2072-4292"],"issn-type":[{"type":"electronic","value":"2072-4292"}],"subject":[],"published":{"date-parts":[[2021,4,27]]}}}