{"url":"/sota/change-detection-on-whu-cd","task":{"name":"Change Detection","url":"/task/change-detection","note":null},"dataset":{"name":"WHU-CD","url":null},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**Change Detection** is a computer vision task that involves detecting changes in an image or video sequence over time. The goal is to identify areas in the image or video that have undergone changes, such as appearance changes, object disappearance or appearance, or even changes in the scene's background.\r\n\r\nImage credit: [\"A TRANSFORMER-BASED SIAMESE NETWORK FOR CHANGE DETECTION\"](https://arxiv.org/pdf/2201.01293v1.pdf)","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["F1","Precision","Recall","Overall Accuracy","KC","IoU"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"F1":"higher","Precision":"higher","Recall":"higher","Overall Accuracy":"higher","KC":null,"IoU":"higher"}},"counts":{"rows":22,"rows_with_code":21,"rows_with_paper_page":22,"rows_dated":22,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"CLAFA-LWGANet L2","metrics":{"F1":"95.24","IoU":"90.92","Precision":"96.51"},"uses_additional_data":false,"paper_date":"2025-01-17","paper":"/paper/lwganet-a-lightweight-group-attention","paper_url":"https://arxiv.org/abs/2501.10040v1","paper_title":"LWGANet: A Lightweight Group Attention Backbone for Remote Sensing Visual Tasks","code":"https://github.com/lwcver/lwganet","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"BiFA","metrics":{"F1":"94.37","IoU":"89.34","Overall Accuracy":"99.56","Precision":"95.15","Recall":"93.60"},"uses_additional_data":false,"paper_date":"2024-03-18","paper":"/paper/bifa-remote-sensing-image-change-detection","paper_url":"https://ieeexplore.ieee.org/abstract/document/10471555/metrics#metrics","paper_title":"BiFA: Remote Sensing Image Change Detection With Bitemporal Feature Alignment","code":"https://github.com/zmoka-zht/BiFA","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"C2FNet","metrics":{"F1":"94.36","IoU":"89.33","KC":"94.14","Overall Accuracy":"99.56","Precision":"96.57","Recall":"92.26"},"uses_additional_data":false,"paper_date":"2024-04-22","paper":"/paper/c2f-semicd-a-coarse-to-fine-semi-supervised","paper_url":"https://arxiv.org/abs/2404.13838v1","paper_title":"C2F-SemiCD: A Coarse-to-Fine Semi-Supervised Change Detection Method Based on Consistency Regularization in High-Resolution Remote Sensing Images","code":"https://github.com/chengxihan/c2f-semicd-and-c2f-cdnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"ChangeMamba","metrics":{"F1":"94.19","IoU":"89.02","KC":"93.98","Overall Accuracy":"99.58","Precision":"96.18","Recall":"92.23"},"uses_additional_data":false,"paper_date":"2024-04-04","paper":"/paper/changemamba-remote-sensing-change-detection","paper_url":"https://arxiv.org/abs/2404.03425v7","paper_title":"ChangeMamba: Remote Sensing Change Detection With Spatiotemporal State Space Model","code":"https://github.com/chenhongruixuan/mambacd","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":4,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"CDMamba","metrics":{"F1":"93.76","IoU":"88.26","Overall Accuracy":"99.51","Precision":"95.58","Recall":"92.01"},"uses_additional_data":false,"paper_date":"2024-06-06","paper":"/paper/cdmamba-remote-sensing-image-change-detection","paper_url":"https://arxiv.org/abs/2406.04207v2","paper_title":"CDMamba: Incorporating Local Clues into Mamba for Remote Sensing Image Binary Change Detection","code":"https://github.com/zmoka-zht/cdmamba","n_code_links":3,"syntology":null},{"rank_in_archive_order":6,"model":"SChanger-base","metrics":{"F1":"93.20"},"uses_additional_data":false,"paper_date":"2025-03-26","paper":"/paper/schanger-change-detection-from-a-semantic","paper_url":"https://arxiv.org/abs/2503.20734v1","paper_title":"SChanger: Change Detection from a Semantic Change and Spatial Consistency Perspective","code":"https://github.com/zhouziyu-cn/SChanger","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"SChanger-small","metrics":{"F1":"93.15"},"uses_additional_data":false,"paper_date":"2025-03-26","paper":"/paper/schanger-change-detection-from-a-semantic","paper_url":"https://arxiv.org/abs/2503.20734v1","paper_title":"SChanger: Change Detection from a Semantic Change and Spatial Consistency Perspective","code":"https://github.com/zhouziyu-cn/SChanger","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"DDPM-CD","metrics":{"F1":"92.65","Overall Accuracy":"99.42"},"uses_additional_data":false,"paper_date":"2022-06-23","paper":"/paper/remote-sensing-change-detection-segmentation","paper_url":"https://arxiv.org/abs/2206.11892v3","paper_title":"DDPM-CD: Denoising Diffusion Probabilistic Models as Feature Extractors for Change Detection","code":"https://github.com/wgcban/ddpm-cd","n_code_links":1,"syntology":{"n_ran":10,"n_unverified":3,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":9,"model":"CGNet","metrics":{"F1":"92.59","IoU":"86.21","KC":"92.33","Overall Accuracy":"99.48","Precision":"94.47","Recall":"90.79"},"uses_additional_data":false,"paper_date":"2024-04-14","paper":"/paper/change-guiding-network-incorporating-change","paper_url":"https://arxiv.org/abs/2404.09179v1","paper_title":"Change Guiding Network: Incorporating Change Prior to Guide Change Detection in Remote Sensing Imagery","code":"https://github.com/chengxihan/cgnet-cd","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"Dsfer-Net","metrics":{"F1":"92.58","IoU":"86.18","Overall Accuracy":"99.46","Precision":"94.17","Recall":"91.04"},"uses_additional_data":false,"paper_date":"2023-04-03","paper":"/paper/dsfer-net-a-deep-supervision-and-feature","paper_url":"https://arxiv.org/abs/2304.01101v2","paper_title":"Dsfer-Net: A Deep Supervision and Feature Retrieval Network for Bitemporal Change Detection Using Modern Hopfield Networks","code":"https://github.com/shizhenchang/dsfer-net","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"LRNet","metrics":{"F1":"92.51","IoU":"86.06","Overall Accuracy":"99.47","Precision":"95.11","Recall":"90.04"},"uses_additional_data":false,"paper_date":"2024-04-07","paper":"/paper/lrnet-change-detection-of-high-resolution","paper_url":"https://arxiv.org/abs/2404.04884v1","paper_title":"LRNet: Change detection of high-resolution remote sensing imagery via strategy of localization-then-refinement","code":"https://github.com/pl-2000/lrnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"HCGMNet","metrics":{"F1":"92.08","IoU":"85.33","KC":"91.80","Overall Accuracy":"99.45","Precision":"93.93","Recall":"90.31"},"uses_additional_data":false,"paper_date":"2023-02-21","paper":"/paper/hcgmnet-a-hierarchical-change-guiding-map","paper_url":"https://arxiv.org/abs/2302.10420v2","paper_title":"HCGMNET: A Hierarchical Change Guiding Map Network For Change Detection","code":"https://github.com/ChengxiHAN/HCGMNet-CD","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"SRC-Net","metrics":{"F1":"92.06","IoU":"85.28","Overall Accuracy":"99.30","Precision":"92.57","Recall":"91.55"},"uses_additional_data":false,"paper_date":"2024-06-09","paper":"/paper/src-net-bi-temporal-spatial-relationship","paper_url":"https://arxiv.org/abs/2406.05668v2","paper_title":"SRC-Net: Bi-Temporal Spatial Relationship Concerned Network for Change Detection","code":"https://github.com/Chnja/SRCNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"RSM-CD","metrics":{"F1":"91.87","IoU":"84.96","Precision":"93.37","Recall":"90.42"},"uses_additional_data":false,"paper_date":"2024-04-03","paper":"/paper/rs-mamba-for-large-remote-sensing-image-dense","paper_url":"https://arxiv.org/abs/2404.02668v2","paper_title":"RS-Mamba for Large Remote Sensing Image Dense Prediction","code":"https://github.com/walking-shadow/Official_Remote_Sensing_Mamba","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":4,"n_samples":6,"n_pointer_only_licence":6}},{"rank_in_archive_order":15,"model":"T-UNet","metrics":{"F1":"91.77","Overall Accuracy":"99.42","Precision":"95.44","Recall":"88.37"},"uses_additional_data":false,"paper_date":"2023-08-04","paper":"/paper/t-unet-triplet-unet-for-change-detection-in","paper_url":"https://arxiv.org/abs/2308.02356v1","paper_title":"T-UNet: Triplet UNet for Change Detection in High-Resolution Remote Sensing Images","code":"https://github.com/pl-2000/t-unet","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"CDMaskFormer","metrics":{"F1":"91.56","IoU":"84.44","Overall Accuracy":"99.23","Precision":"92.25","Recall":"90.89"},"uses_additional_data":false,"paper_date":"2024-06-21","paper":"/paper/rethinking-remote-sensing-change-detection","paper_url":"https://arxiv.org/abs/2406.15320v1","paper_title":"Rethinking Remote Sensing Change Detection With A Mask View","code":"https://github.com/xwmaxwma/rschange","n_code_links":1,"syntology":null},{"rank_in_archive_order":17,"model":"RFL-CDNet","metrics":{"F1":"91.39","Precision":"91.33","Recall":"91.46"},"uses_additional_data":false,"paper_date":"2024-04-27","paper":"/paper/rfl-cdnet-towards-accurate-change-detection","paper_url":"https://arxiv.org/abs/2404.17765v1","paper_title":"RFL-CDNet: Towards Accurate Change Detection via Richer Feature Learning","code":"https://github.com/hhaizee/rfl-cdnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"Tiny-CD","metrics":{"F1":"91.05","IoU":"83.57","Overall Accuracy":"99.10","Precision":"92.68","Recall":"89.47"},"uses_additional_data":false,"paper_date":"2022-07-26","paper":"/paper/tinycd-a-not-so-deep-learning-model-for","paper_url":"https://arxiv.org/abs/2207.13159v2","paper_title":"TINYCD: A (Not So) Deep Learning Model For Change Detection","code":"https://github.com/likyoo/open-cd","n_code_links":2,"syntology":null},{"rank_in_archive_order":19,"model":"DDLNet","metrics":{"F1":"90.56","IoU":"82.75","Overall Accuracy":"99.13","Precision":"91.56","Recall":"90.03"},"uses_additional_data":false,"paper_date":"2024-06-19","paper":"/paper/ddlnet-boosting-remote-sensing-change","paper_url":"https://arxiv.org/abs/2406.13606v1","paper_title":"DDLNet: Boosting Remote Sensing Change Detection with Dual-Domain Learning","code":"https://github.com/xwmaxwma/rschange","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"DTCDSCN","metrics":{"F1":"89.75","IoU":"81.40","Precision":"90.15","Recall":"89.35"},"uses_additional_data":false,"paper_date":"2019-09-17","paper":"/paper/building-change-detection-for-remote-sensing","paper_url":"https://arxiv.org/abs/1909.07726v1","paper_title":"Building Change Detection for Remote Sensing Images Using a Dual Task Constrained Deep Siamese Convolutional Network Model","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":21,"model":"HANet","metrics":{"F1":"88.16","IoU":"78.82","KC":"87.72","Overall Accuracy":"99.16","Precision":"88.30","Recall":"88.01"},"uses_additional_data":false,"paper_date":"2024-04-14","paper":"/paper/hanet-a-hierarchical-attention-network-for","paper_url":"https://arxiv.org/abs/2404.09178v1","paper_title":"HANet: A Hierarchical Attention Network for Change Detection With Bitemporal Very-High-Resolution Remote Sensing Images","code":"https://github.com/chengxihan/hanet-cd","n_code_links":1,"syntology":null},{"rank_in_archive_order":22,"model":"STNet","metrics":{"F1":"87.46","IoU":"77.72","Overall Accuracy":"98.85","Precision":"87.84","Recall":"87.08"},"uses_additional_data":false,"paper_date":"2023-04-22","paper":"/paper/stnet-spatial-and-temporal-feature-fusion","paper_url":"https://arxiv.org/abs/2304.11422v1","paper_title":"STNet: Spatial and Temporal feature fusion network for change detection in remote sensing images","code":"https://github.com/xwmaxwma/rschange","n_code_links":1,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":3,"rows_with_any_sample_ran":3,"distinct_papers_with_graph_line":3,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":17,"n_unverified":11,"n_samples":28,"n_pointer_only_licence":6,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":17,"n_unverified":11,"n_samples":28,"n_pointer_only_licence":6,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}