Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386133645> ?p ?o ?g. }
- W4386133645 endingPage "113779" @default.
- W4386133645 startingPage "113779" @default.
- W4386133645 abstract "Accurate change detection of built-up areas (BAs) fosters a comprehensive understanding of urban development. The post-classification comparison (PCC) is a widely-used change detection method by classification and temporal comparison. For classification, image-level labeling is an efficient alternative to pixel-level one for pixel-wise weakly supervised segmentation, which frequently applies pixel-level pseudo labels generated from class activation map (CAM) to train semantic segmentation networks. CAM can be obtained from classification networks trained with image-level labels and can indicate the spatial location of objects. The existing studies are subject to the following issues: 1) They only rely on the single-scale and low-resolution CAM, but ignore the multi-scale property of BAs; 2) Pixel-level pseudo labels usually contain noises (e.g., omissions and false alarms); 3) The temporal correlation between multi-temporal images is less considered in PCC. To address these limitations, this paper proposed a multi-scale weakly supervised learning method, which utilized a large number of single-temporal high-resolution images and image-level labels to detect BA changes. This method consisted of three modules: 1) multi-scale CAM for BA pseudo label generation; 2) adaptive online noise correction for BA detection; and 3) generation of reliable pseudo labels for BA change detection. Based on ZY-3 images (2.5 m), we constructed the first multi-view datasets for both BA detection and change detection. Each ZY-3 image includes a multi-spectral image with red, green, blue, and near-infrared bands and a multi-view image with nadir-, forward-, and backward-views. The BA detection dataset contained 86,166 image-level samples (256 × 256 pixels for each sample), covering 48 major cities in China, while the BA change detection dataset consisted of ZY-3 bi-temporal images at rapidly urbanizing areas (i.e., Beijing and Shanghai). Experiments showed that the proposed method can detect BA changes and suppress pseudo changes effectively, yielding 88.2% F1-score in BA detection and 79.3% for Shanghai and 78.5% for Beijing in change detection. Further analysis demonstrated the proposed method to be advantageous in the following two fronts: 1) the image-level weak labels can achieve pixel-wise BA change detection at low cost; and 2) the multi-scale CAM and temporal correlation are effective in the scenarios with limited labels. Datasets and codes will be accessed at https://github.com/lauraset/MSWS." @default.
- W4386133645 created "2023-08-25" @default.
- W4386133645 creator A5004755532 @default.
- W4386133645 creator A5031729932 @default.
- W4386133645 creator A5072661100 @default.
- W4386133645 date "2023-11-01" @default.
- W4386133645 modified "2023-10-14" @default.
- W4386133645 title "A multi-scale weakly supervised learning method with adaptive online noise correction for high-resolution change detection of built-up areas" @default.
- W4386133645 cites W1905190183 @default.
- W4386133645 cites W1984792953 @default.
- W4386133645 cites W2022841949 @default.
- W4386133645 cites W2036798369 @default.
- W4386133645 cites W2043244602 @default.
- W4386133645 cites W2083863337 @default.
- W4386133645 cites W2085665642 @default.
- W4386133645 cites W2089702680 @default.
- W4386133645 cites W2094455438 @default.
- W4386133645 cites W2109683954 @default.
- W4386133645 cites W2127199143 @default.
- W4386133645 cites W2131438174 @default.
- W4386133645 cites W2133059825 @default.
- W4386133645 cites W2154028886 @default.
- W4386133645 cites W2157026765 @default.
- W4386133645 cites W2161570034 @default.
- W4386133645 cites W2168809519 @default.
- W4386133645 cites W2181914484 @default.
- W4386133645 cites W2610884537 @default.
- W4386133645 cites W2615543373 @default.
- W4386133645 cites W2741377155 @default.
- W4386133645 cites W2746791238 @default.
- W4386133645 cites W2806603867 @default.
- W4386133645 cites W2898070142 @default.
- W4386133645 cites W2911648799 @default.
- W4386133645 cites W2924638668 @default.
- W4386133645 cites W2952259003 @default.
- W4386133645 cites W2990622733 @default.
- W4386133645 cites W3000627240 @default.
- W4386133645 cites W3010317891 @default.
- W4386133645 cites W3015756600 @default.
- W4386133645 cites W3022476827 @default.
- W4386133645 cites W3042609801 @default.
- W4386133645 cites W3086458417 @default.
- W4386133645 cites W3133962853 @default.
- W4386133645 cites W3169100537 @default.
- W4386133645 cites W3187173039 @default.
- W4386133645 cites W4206303381 @default.
- W4386133645 cites W4221144214 @default.
- W4386133645 cites W4221161499 @default.
- W4386133645 cites W4226253382 @default.
- W4386133645 cites W4283450732 @default.
- W4386133645 cites W4291018768 @default.
- W4386133645 cites W4292543266 @default.
- W4386133645 cites W4294982551 @default.
- W4386133645 cites W4321194933 @default.
- W4386133645 doi "https://doi.org/10.1016/j.rse.2023.113779" @default.
- W4386133645 hasPublicationYear "2023" @default.
- W4386133645 type Work @default.
- W4386133645 citedByCount "0" @default.
- W4386133645 crossrefType "journal-article" @default.
- W4386133645 hasAuthorship W4386133645A5004755532 @default.
- W4386133645 hasAuthorship W4386133645A5031729932 @default.
- W4386133645 hasAuthorship W4386133645A5072661100 @default.
- W4386133645 hasConcept C115961682 @default.
- W4386133645 hasConcept C124504099 @default.
- W4386133645 hasConcept C153180895 @default.
- W4386133645 hasConcept C154945302 @default.
- W4386133645 hasConcept C160633673 @default.
- W4386133645 hasConcept C203595873 @default.
- W4386133645 hasConcept C205372480 @default.
- W4386133645 hasConcept C205649164 @default.
- W4386133645 hasConcept C2778755073 @default.
- W4386133645 hasConcept C31972630 @default.
- W4386133645 hasConcept C41008148 @default.
- W4386133645 hasConcept C58640448 @default.
- W4386133645 hasConcept C62649853 @default.
- W4386133645 hasConcept C89600930 @default.
- W4386133645 hasConcept C99498987 @default.
- W4386133645 hasConceptScore W4386133645C115961682 @default.
- W4386133645 hasConceptScore W4386133645C124504099 @default.
- W4386133645 hasConceptScore W4386133645C153180895 @default.
- W4386133645 hasConceptScore W4386133645C154945302 @default.
- W4386133645 hasConceptScore W4386133645C160633673 @default.
- W4386133645 hasConceptScore W4386133645C203595873 @default.
- W4386133645 hasConceptScore W4386133645C205372480 @default.
- W4386133645 hasConceptScore W4386133645C205649164 @default.
- W4386133645 hasConceptScore W4386133645C2778755073 @default.
- W4386133645 hasConceptScore W4386133645C31972630 @default.
- W4386133645 hasConceptScore W4386133645C41008148 @default.
- W4386133645 hasConceptScore W4386133645C58640448 @default.
- W4386133645 hasConceptScore W4386133645C62649853 @default.
- W4386133645 hasConceptScore W4386133645C89600930 @default.
- W4386133645 hasConceptScore W4386133645C99498987 @default.
- W4386133645 hasFunder F4320321001 @default.
- W4386133645 hasLocation W43861336451 @default.
- W4386133645 hasOpenAccess W4386133645 @default.
- W4386133645 hasPrimaryLocation W43861336451 @default.
- W4386133645 hasRelatedWork W1604511055 @default.
- W4386133645 hasRelatedWork W1669643531 @default.