{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/frequency-temporal-attention-network-for-1","title":"Frequency-Temporal Attention Network for Remote Sensing Imagery Change Detection","arxiv_id":null,"date":"2024-10-10","proceeding":"IEEE Geoscience and Remote Sensing Letters 2024 10","authors":["Chunyan Yu; Haobo Li; Yabin Hu; Qiang Zhang; Meiping Song; Yulei Wang;"],"abstract":"Change detection (CD) in remote sensing imagery is identified as a pivotal task in the field of Earth observation, while it usually confronts the dilemma of intricate data and minor alterations. To address the stated challenge, this letter presents an innovative frequency-temporal attention network for CD (FTAN), which incorporates two advanced modules including the multidimensional convolutional frequency attention module (MCFA) and the interactive attention module (IAM). Specifically, the MCFA module is essential for enhancing sensitivity in CD by merging multiscale spatial and frequency domain features. As a supplement to MCFA, the IAM aggregates category-related tokens and processes cross-attention information from different time phases. The seamless integration of MCFA and IAM empowers the FTAN network with enhanced capabilities to detect minor regions and edges accurately. Experiments on datasets like LEVIR-CD and DSIFN-CD demonstrate superior performance by outperforming existing models in F1 scores and IoU metrics. Our code and pretrained models will be released at https://github.com/chirsycy/FTAN .","url_abs":"https://ieeexplore.ieee.org/document/10713423","url_pdf":"https://ieeexplore.ieee.org/document/10713423","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"frequency-temporal-attention-network-for-1","repo_url":"https://github.com/haobosang/FTAN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"change-detection","task_name":"Change Detection"},{"task_slug":"earth-observation","task_name":"Earth Observation"},{"task_slug":"image-classification","task_name":"Image Classification"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"multi-attention-network","method_name":"Multi-Attention Network"},{"method_slug":"mcfa","method_name":"Multidimensional Convolutional Frequency Attention"},{"method_slug":"siamese-network","method_name":"Siamese Network"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/change-detection-on-dsifn-cd","task":"Change Detection","dataset":"DSIFN-CD","model":"FTAN","rank_in_archive_order":2,"of":9,"metrics":{"F1":"89.56","IoU":"81.10","Precision":"90.54","Recall":"88.61"},"uses_additional_data":false},{"leaderboard":"/sota/change-detection-on-levir-cd","task":"Change Detection","dataset":"LEVIR-CD","model":"FTAN","rank_in_archive_order":23,"of":28,"metrics":{"F1":"90.51","IoU":"82.78","Precision":"92.41","Recall":"88.82"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}