{"title":"基于标签噪声自适应全卷积神经网络的GIS监控建筑提取","authors":"Zenghui Zhang, Weiwei Guo, Mingjie Li, Wenxian Yu","doi":"10.1109/LGRS.2019.2963065","DOIUrl":null,"url":null,"abstract":"Automatic building extraction from aerial or satellite images is a dense pixel prediction task for many applications. It demands a large number of clean label data to train a deep neural network for building extraction. But it is labor expensive to collect such pixel-wise annotated data manually. Fortunately, the building footprint data of geographic information system (GIS) maps provide a cheap way of generating building label data, but these labels are imperfect due to misalignment between the GIS maps and images. In this letter, we consider the task of learning a deep neural network to label images pixel-wise from such noisy label data for building extraction. To this end, we propose a general label noise-adaptive (NA) neural network framework consisting of a base network followed by an additional probability transition modular (PTM) which is introduced to capture the relationship between the true label and the noisy label. The parameters of the PTM can be estimated as part of the training process of the whole network by the off-the-shelf backpropagation algorithm. We conduct experiments on real-world data set to demonstrate that our proposed PTM can better handle noisy labels and improve the performance of convolutional neural networks (CNNs) trained on the noisy label data generated by GIS maps for building extraction. The experimental results indicate that being armed with our proposed PTM for fully CNN, it provides a promising solution to reduce manual annotation effort for the labor-expensive object extraction tasks from remote sensing images.","PeriodicalId":13046,"journal":{"name":"IEEE Geoscience and Remote Sensing Letters","volume":"17 1","pages":"2135-2139"},"PeriodicalIF":4.0000,"publicationDate":"2020-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/LGRS.2019.2963065","citationCount":"35","resultStr":"{\"title\":\"GIS-Supervised Building Extraction With Label Noise-Adaptive Fully Convolutional Neural Network\",\"authors\":\"Zenghui Zhang, Weiwei Guo, Mingjie Li, Wenxian Yu\",\"doi\":\"10.1109/LGRS.2019.2963065\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Automatic building extraction from aerial or satellite images is a dense pixel prediction task for many applications. It demands a large number of clean label data to train a deep neural network for building extraction. But it is labor expensive to collect such pixel-wise annotated data manually. Fortunately, the building footprint data of geographic information system (GIS) maps provide a cheap way of generating building label data, but these labels are imperfect due to misalignment between the GIS maps and images. In this letter, we consider the task of learning a deep neural network to label images pixel-wise from such noisy label data for building extraction. To this end, we propose a general label noise-adaptive (NA) neural network framework consisting of a base network followed by an additional probability transition modular (PTM) which is introduced to capture the relationship between the true label and the noisy label. The parameters of the PTM can be estimated as part of the training process of the whole network by the off-the-shelf backpropagation algorithm. We conduct experiments on real-world data set to demonstrate that our proposed PTM can better handle noisy labels and improve the performance of convolutional neural networks (CNNs) trained on the noisy label data generated by GIS maps for building extraction. The experimental results indicate that being armed with our proposed PTM for fully CNN, it provides a promising solution to reduce manual annotation effort for the labor-expensive object extraction tasks from remote sensing images.\",\"PeriodicalId\":13046,\"journal\":{\"name\":\"IEEE Geoscience and Remote Sensing Letters\",\"volume\":\"17 1\",\"pages\":\"2135-2139\"},\"PeriodicalIF\":4.0000,\"publicationDate\":\"2020-01-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://sci-hub-pdf.com/10.1109/LGRS.2019.2963065\",\"citationCount\":\"35\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Geoscience and Remote Sensing Letters\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1109/LGRS.2019.2963065\",\"RegionNum\":3,\"RegionCategory\":\"地球科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ENGINEERING, ELECTRICAL & ELECTRONIC\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Geoscience and Remote Sensing Letters","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1109/LGRS.2019.2963065","RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
GIS-Supervised Building Extraction With Label Noise-Adaptive Fully Convolutional Neural Network
Automatic building extraction from aerial or satellite images is a dense pixel prediction task for many applications. It demands a large number of clean label data to train a deep neural network for building extraction. But it is labor expensive to collect such pixel-wise annotated data manually. Fortunately, the building footprint data of geographic information system (GIS) maps provide a cheap way of generating building label data, but these labels are imperfect due to misalignment between the GIS maps and images. In this letter, we consider the task of learning a deep neural network to label images pixel-wise from such noisy label data for building extraction. To this end, we propose a general label noise-adaptive (NA) neural network framework consisting of a base network followed by an additional probability transition modular (PTM) which is introduced to capture the relationship between the true label and the noisy label. The parameters of the PTM can be estimated as part of the training process of the whole network by the off-the-shelf backpropagation algorithm. We conduct experiments on real-world data set to demonstrate that our proposed PTM can better handle noisy labels and improve the performance of convolutional neural networks (CNNs) trained on the noisy label data generated by GIS maps for building extraction. The experimental results indicate that being armed with our proposed PTM for fully CNN, it provides a promising solution to reduce manual annotation effort for the labor-expensive object extraction tasks from remote sensing images.
期刊介绍:
IEEE Geoscience and Remote Sensing Letters (GRSL) is a monthly publication for short papers (maximum length 5 pages) addressing new ideas and formative concepts in remote sensing as well as important new and timely results and concepts. Papers should relate to the theory, concepts and techniques of science and engineering as applied to sensing the earth, oceans, atmosphere, and space, and the processing, interpretation, and dissemination of this information. The technical content of papers must be both new and significant. Experimental data must be complete and include sufficient description of experimental apparatus, methods, and relevant experimental conditions. GRSL encourages the incorporation of "extended objects" or "multimedia" such as animations to enhance the shorter papers.