{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T12:49:47Z","timestamp":1765889387391,"version":"build-2065373602"},"reference-count":52,"publisher":"MDPI AG","issue":"18","license":[{"start":{"date-parts":[[2024,9,18]],"date-time":"2024-09-18T00:00:00Z","timestamp":1726617600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012138","name":"Beijing Forestry University","doi-asserted-by":"publisher","award":["BLX202363"],"award-info":[{"award-number":["BLX202363"]}],"id":[{"id":"10.13039\/501100012138","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Building change detection (BCD) from remote sensing images is an essential field for urban studies. In this well-developed field, Convolutional Neural Networks (CNNs) and Transformer have been leveraged to empower BCD models in handling multi-scale information. However, it is still challenging to accurately detect subtle changes using current models, which has been the main bottleneck to improving detection accuracy. In this paper, a multi-scale differential feature self-attention network (MDFA-Net) is proposed to effectively integrate CNN and Transformer by balancing the global receptive field from the self-attention mechanism and the local receptive field from convolutions. In MDFA-Net, two innovative modules were designed. Particularly, a hierarchical multi-scale dilated convolution (HMDConv) module was proposed to extract local features with hybrid dilation convolutions, which can ameliorate the effect of CNN\u2019s local bias. In addition, a differential feature self-attention (DFA) module was developed to implement the self-attention mechanism at multi-scale difference feature maps to overcome the problem that local details may be lost in the global receptive field in Transformer. The proposed MDFA-Net achieves state-of-the-art accuracy performance in comparison with related works, e.g., USSFC-Net, in three open datasets: WHU-CD, CDD-CD, and LEVIR-CD. Based on the experimental results, MDFA-Net significantly exceeds other models in F1 score, IoU, and overall accuracy; the F1 score is 93.81%, 95.52%, and 91.21% in WHU-CD, CDD-CD, and LEVIR-CD datasets, respectively. Furthermore, MDFA-Net achieved first or second place in precision and recall in the test in all three datasets, which indicates its better balance in precision and recall than other models. We also found that subtle changes, i.e., small-sized building changes and irregular boundary changes, are better detected thanks to the introduction of HMDConv and DFA. To this end, with its better ability to leverage multi-scale differential information than traditional methods, MDFA-Net provides a novel and effective avenue to integrate CNN and Transformer in BCD. Further studies could focus on improving the model\u2019s insensitivity to hyper-parameters and the model\u2019s generalizability in practical applications.<\/jats:p>","DOI":"10.3390\/rs16183466","type":"journal-article","created":{"date-parts":[[2024,9,19]],"date-time":"2024-09-19T03:34:20Z","timestamp":1726716860000},"page":"3466","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["MDFA-Net: Multi-Scale Differential Feature Self-Attention Network for Building Change Detection in Remote Sensing Images"],"prefix":"10.3390","volume":"16","author":[{"given":"Yuanling","family":"Li","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, Beijing Forestry University, Beijing 100083, China"},{"name":"Engineering Research Center for Forestry-Oriented Intelligent Information Processing of National Forestry and Grassland Administration, Beijing 100083, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6619-5029","authenticated-orcid":false,"given":"Shengyuan","family":"Zou","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Beijing Forestry University, Beijing 100083, China"},{"name":"Engineering Research Center for Forestry-Oriented Intelligent Information Processing of National Forestry and Grassland Administration, Beijing 100083, China"}]},{"given":"Tianzhong","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Beijing Forestry University, Beijing 100083, China"},{"name":"Engineering Research Center for Forestry-Oriented Intelligent Information Processing of National Forestry and Grassland Administration, Beijing 100083, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7608-0797","authenticated-orcid":false,"given":"Xiaohui","family":"Su","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Beijing Forestry University, Beijing 100083, China"},{"name":"Engineering Research Center for Forestry-Oriented Intelligent Information Processing of National Forestry and Grassland Administration, Beijing 100083, China"}]}],"member":"1968","published-online":{"date-parts":[[2024,9,18]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"989","DOI":"10.1080\/01431168908903939","article-title":"Review article digital change detection techniques using remotely-sensed data","volume":"10","author":"Singh","year":"1989","journal-title":"Int. J. Remote Sens."},{"key":"ref_2","first-page":"123","article-title":"A comprehensive study on remote sensing techniques","volume":"62","author":"Smith","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"5630613","DOI":"10.1109\/TGRS.2022.3203314","article-title":"Change detection meets visual question answering","volume":"60","author":"Yuan","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"811","DOI":"10.1109\/LGRS.2020.2988032","article-title":"Building change detection for remote sensing images using a dual-task constrained deep Siamese convolutional network model","volume":"18","author":"Liu","year":"2020","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/j.isprsjprs.2016.03.014","article-title":"A survey on object detection in optical remote sensing images","volume":"117","author":"Cheng","year":"2016","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"4363","DOI":"10.1109\/TGRS.2015.2396686","article-title":"Sequential spectral change vector analysis for iteratively discovering and detecting multiple changes in hyperspectral images","volume":"53","author":"Liu","year":"2015","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1016\/j.isprsjprs.2018.11.014","article-title":"Multispectral change detection using multivariate Kullback-Leibler distance","volume":"147","author":"Jabari","year":"2019","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_8","unstructured":"Huang, L., Zhang, G., and Li, Y. (2010, January 6\u20137). An object-based change detection approach by integrating intensity and texture differences. Proceedings of the 2010 2nd International Asia Conference on Informatics in Control, Automation and Robotics (CAR 2010), Wuhan, China."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1109\/TNNLS.2015.2435783","article-title":"Change detection in synthetic aperture radar images based on deep neural networks","volume":"27","author":"Gong","year":"2015","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_10","first-page":"102348","article-title":"ADS-Net: An attention-based deeply supervised network for remote sensing image change detection","volume":"101","author":"Wang","year":"2021","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_11","first-page":"4223","article-title":"Multi-scale feature model for object detection","volume":"29","author":"Shen","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"ref_12","first-page":"4567","article-title":"End-to-end superpixel-enhanced network for semantic segmentation","volume":"32","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1016\/j.isprsjprs.2020.06.003","article-title":"A deeply supervised image fusion network for change detection in high resolution bi-temporal remote sensing images","volume":"166","author":"Zhang","year":"2020","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_14","first-page":"100898","article-title":"A deep learning classification approach using high spatial satellite images for detection of built-up areas in rural zones: Case study of Souss-Massa region, Morocco","volume":"29","author":"Wahbi","year":"2023","journal-title":"Remote Sens. Appl. Soc. Environ."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Yang, G., Tang, H., Ding, M., Sebe, N., and Ricci, E. (2021, January 11\u201317). Transformer-based attention networks for continuous pixel-wise prediction. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, BC, Canada.","DOI":"10.1109\/ICCV48922.2021.01596"},{"key":"ref_16","first-page":"15607514","article-title":"Remote sensing image change detection with transformers","volume":"60","author":"Chen","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Cheng, G., Huang, Y., Li, X., Lyu, S., Xu, Z., Zhao, H., Zhao, Q., and Xiang, S. (2024). Change detection methods for remote sensing in the last decade: A comprehensive review. Remote Sens., 16.","DOI":"10.3390\/rs16132355"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Zang, J., Lian, C., Xu, B., Zhang, Z., Su, Y., and Xue, C. (2023). AmtNet: Attentional multi-scale temporal network for phonocardiogram signal classification. Biomed. Signal Process. Control, 85.","DOI":"10.1016\/j.bspc.2023.104934"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"599","DOI":"10.1016\/j.isprsjprs.2023.07.001","article-title":"An attention-based multiscale transformer network for remote sensing image change detection","volume":"202","author":"Liu","year":"2023","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_20","first-page":"103961","article-title":"A context-structural feature decoupling change detection network for detecting earthquake-triggered damage","volume":"131","author":"Zheng","year":"2024","journal-title":"ISPRS Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"4402114","DOI":"10.1109\/TGRS.2023.3261273","article-title":"Ultralightweight spatial\u2013spectral feature cooperation network for change detection in remote sensing images","volume":"61","author":"Lei","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Lin, H., Wang, X., Li, M., Huang, D., and Wu, R. (2023). A multi-task consistency enhancement network for semantic change detection in HR remote sensing images and application of non-agriculturalization. Remote Sens., 15.","DOI":"10.3390\/rs15215106"},{"key":"ref_23","first-page":"5610315","article-title":"ConvTransNet: A CNN\u2013transformer network for change detection with multiscale global\u2013local representations","volume":"61","author":"Li","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_24","unstructured":"Daudt, R.C., Le Saux, B., and Boulch, A. (2018, January 7\u201310). Fully convolutional Siamese networks for change detection. Proceedings of the 25th IEEE International Conference on Image Processing (ICIP), Athens, Greece."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"He, Y., Zhang, H., Ning, X., Zhang, R., Chang, D., and Hao, M. (2023). Spatial-Temporal Semantic Perception Network for Remote Sensing Image Semantic Change Detection. Remote Sens., 15.","DOI":"10.3390\/rs15164095"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1016\/j.isprsjprs.2022.05.001","article-title":"Semantic feature-constrained multitask siamese network for building change detection in high-spatial-resolution remote sensing imagery","volume":"189","author":"Shen","year":"2022","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"8007805","DOI":"10.1109\/LGRS.2021.3056416","article-title":"SNUNet-CD: A densely connected Siamese network for change detection of VHR images","volume":"19","author":"Fang","year":"2022","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Lin, T.Y., and Le, Q.V. (2019, January 15\u201319). NAS-FPN: Learning scalable feature pyramid architecture for object detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00720"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"2728","DOI":"10.1109\/JSTARS.2023.3246564","article-title":"Multi-scale fast Fourier transform based attention network for remote-sensing image super-resolution","volume":"16","author":"Wang","year":"2023","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_30","first-page":"5617116","article-title":"AERNet: An attention-guided edge refinement network and a dataset for remote sensing building change detection","volume":"61","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"6625688","DOI":"10.1155\/2021\/6625688","article-title":"R2AU-Net: Attention recurrent residual convolutional neural network for multimodal medical image segmentation","volume":"2021","author":"Zuo","year":"2021","journal-title":"Secur. Commun. Netw."},{"key":"ref_32","first-page":"5602812","article-title":"Lightweight remote sensing change detection with progressive feature aggregation and supervised attention","volume":"61","author":"Li","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_33","first-page":"5600417","article-title":"A triple-stream network with cross-stage feature fusion for high-resolution image change detection","volume":"61","author":"Zhao","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Li, L., Liu, H., Li, Q., Tian, Z., Li, Y., Geng, W., and Wang, S. (2023). Near-infrared blood vessel image segmentation using background subtraction and improved mathematical morphology. Bioengineering, 10.","DOI":"10.3390\/bioengineering10060726"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., and Kweon, I.S. (2018, January 8\u201314). CBAM: Convolutional Block Attention Module. Proceedings of the European Conference on Computer Vision (ECCV 2018), Munich, Germany.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1016\/j.isprsjprs.2022.02.021","article-title":"FCCDN: Feature constraint network for VHR image change detection","volume":"187","author":"Chen","year":"2022","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Jiang, H., Hu, X., Li, K., Zhang, J., Gong, J., and Zhang, M. (2020). PGA-SiamNet: Pyramid feature-based attention-guided Siamese network for remote sensing orthoimagery building change detection. Remote Sens., 12.","DOI":"10.3390\/rs12030484"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"5521614","DOI":"10.1109\/TGRS.2021.3139077","article-title":"A Spectral and Spatial Attention Network for Change Detection in Hyperspectral Images","volume":"60","author":"Gong","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_39","first-page":"1","article-title":"ChangeFormer: A Change Detection Framework Based on Transformer for Remote Sensing Images","volume":"60","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_40","first-page":"4401015","article-title":"Change Detection on Remote Sensing Images Using Dual-Branch Multilevel Intertemporal Network","volume":"61","author":"Feng","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Ma, H., Zhao, L., Li, B., Niu, R., and Wang, Y. (2023). Change Detection Needs Neighborhood Interaction in Transformer. Remote Sens., 15.","DOI":"10.3390\/rs15235459"},{"key":"ref_42","first-page":"5611615","article-title":"Relation changes matter: Cross-temporal difference transformer for change detection in remote sensing images","volume":"61","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Wang, Y., Wang, M., Hao, Z., Wang, Q., Wang, Q., and Ye, Y. (2024). MSGFNet: Multi-Scale Gated Fusion Network for Remote Sensing Image Change Detection. Remote Sens., 16.","DOI":"10.3390\/rs16030572"},{"key":"ref_44","unstructured":"Li, D., Li, L., Chen, Z., and Li, J. (2024). Shift-ConvNets: Small convolutional kernel with large kernel effects. arXiv."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Fan, C.-L. (2024). Multiscale Feature Extraction by Using Convolutional Neural Network: Extraction of Objects from Multiresolution Images of Urban Areas. ISPRS Int. J. Geo-Inf., 13.","DOI":"10.3390\/ijgi13010005"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Li, D., Yao, A., and Chen, Q. (2020, January 23\u201328). PSConv: Squeezing Feature Pyramid into One Compact Poly-Scale Convolutional Layer. Proceedings of the European Conference on Computer Vision (ECCV), Cham, Switzerland.","DOI":"10.1007\/978-3-030-58589-1_37"},{"key":"ref_47","first-page":"85","article-title":"Attention Mechanisms for Change Detection in Remote Sensing: A Comprehensive Review","volume":"194","author":"Guo","year":"2023","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"574","DOI":"10.1109\/TGRS.2018.2858817","article-title":"Fully convolutional networks for multisource building extraction from an open aerial and satellite imagery data set","volume":"57","author":"Ji","year":"2019","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"565","DOI":"10.5194\/isprs-archives-XLII-2-565-2018","article-title":"Change detection in remote sensing images using conditional adversarial networks","volume":"42","author":"Lebedev","year":"2018","journal-title":"Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Chen, H., and Shi, Z. (2020). A spatial-temporal attention-based method and a new dataset for remote sensing image change detection. Remote Sens., 12.","DOI":"10.3390\/rs12101662"},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"8471","DOI":"10.1007\/s00521-022-08122-3","article-title":"TINYCD: A (not so) deep learning model for change detection","volume":"35","author":"Codegoni","year":"2023","journal-title":"Neural Comput. Appl."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"105254","DOI":"10.1016\/j.engappai.2022.105254","article-title":"Deep and transfer learning for building occupancy detection: A review and comparative analysis","volume":"115","author":"Sayed","year":"2022","journal-title":"Eng. Appl. Artif. Intell."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/16\/18\/3466\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T15:58:57Z","timestamp":1760111937000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/16\/18\/3466"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,18]]},"references-count":52,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2024,9]]}},"alternative-id":["rs16183466"],"URL":"https:\/\/doi.org\/10.3390\/rs16183466","relation":{},"ISSN":["2072-4292"],"issn-type":[{"type":"electronic","value":"2072-4292"}],"subject":[],"published":{"date-parts":[[2024,9,18]]}}}