{"url":"/sota/semantic-segmentation-on-isprs-potsdam","task":{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","note":null},"dataset":{"name":"ISPRS Potsdam","url":"/dataset/isprs-potsdam"},"category":"Computer Vision","categories":["Computer Code","Computer Vision","Medical","Robots"],"category_note":null,"description":null,"description_from":null,"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":["Overall Accuracy","Mean F1","Mean IoU"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Overall Accuracy":"higher","Mean F1":"higher","Mean IoU":"higher"}},"counts":{"rows":20,"rows_with_code":16,"rows_with_paper_page":20,"rows_dated":20,"rows_using_additional_data":12},"rows":[{"rank_in_archive_order":1,"model":"AerialFormer-B","metrics":{"Mean F1":"94.1","Mean IoU":"89.1","Overall Accuracy":"93.9"},"uses_additional_data":false,"paper_date":"2023-06-12","paper":"/paper/aerialformer-multi-resolution-transformer-for","paper_url":"https://arxiv.org/abs/2306.06842v2","paper_title":"AerialFormer: Multi-resolution Transformer for Aerial Image Segmentation","code":"https://github.com/UARK-AICV/AerialFormer","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"ViT-G12X4","metrics":{"Mean F1":"92.12","Overall Accuracy":"92.58"},"uses_additional_data":false,"paper_date":"2023-04-11","paper":"/paper/a-billion-scale-foundation-model-for-remote","paper_url":"https://arxiv.org/abs/2304.05215v4","paper_title":"A Billion-scale Foundation Model for Remote Sensing Images","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"FT-UNetFormer","metrics":{"Mean F1":"93.3","Mean IoU":"87.5","Overall Accuracy":"92.0"},"uses_additional_data":true,"paper_date":"2021-09-18","paper":"/paper/efficient-hybrid-transformer-learning-global","paper_url":"https://arxiv.org/abs/2109.08937v4","paper_title":"UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagery","code":"https://github.com/WangLibo1995/GeoSeg","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":4,"model":"DC-Swin","metrics":{"Mean F1":"93.25","Mean IoU":"87.56","Overall Accuracy":"92.0"},"uses_additional_data":true,"paper_date":"2021-04-25","paper":"/paper/transformer-meets-dcfam-a-novel-semantic","paper_url":"https://arxiv.org/abs/2104.12137v6","paper_title":"A Novel Transformer Based Semantic Segmentation Scheme for Fine-Resolution Remote Sensing Images","code":"https://github.com/WangLibo1995/GeoSeg","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":5,"model":"LSKNet-S","metrics":{"Mean F1":"93.1","Mean IoU":"87.2","Overall Accuracy":"92.0"},"uses_additional_data":false,"paper_date":"2024-03-18","paper":"/paper/lsknet-a-foundation-lightweight-backbone-for","paper_url":"https://arxiv.org/abs/2403.11735v5","paper_title":"LSKNet: A Foundation Lightweight Backbone for Remote Sensing","code":"https://github.com/zcablii/lsknet","n_code_links":2,"syntology":null},{"rank_in_archive_order":6,"model":"EfficientUNets and Transformers","metrics":{"Mean F1":"93.7","Overall Accuracy":"91.8"},"uses_additional_data":true,"paper_date":"2022-06-20","paper":"/paper/semantic-labeling-of-high-resolution-images","paper_url":"https://arxiv.org/abs/2206.09731v2","paper_title":"Semantic Labeling of High Resolution Images Using EfficientUNets and Transformers","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"IMP-ViTAEv2-S-UperNet","metrics":{"Overall Accuracy":"91.6"},"uses_additional_data":true,"paper_date":"2022-04-06","paper":"/paper/an-empirical-study-of-remote-sensing","paper_url":"https://arxiv.org/abs/2204.02825v4","paper_title":"An Empirical Study of Remote Sensing Pretraining","code":"https://github.com/vitae-transformer/vitae-transformer-remote-sensing","n_code_links":2,"syntology":null},{"rank_in_archive_order":8,"model":"MANet","metrics":{"Overall Accuracy":"91.318"},"uses_additional_data":true,"paper_date":"2021-05-15","paper":"/paper/multiattention-network-for-semantic","paper_url":"https://ieeexplore.ieee.org/abstract/document/9487010","paper_title":"Multiattention network for semantic segmentation of fine-resolution remote sensing images","code":"https://github.com/lironui/Multi-Attention-Network","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"UNetFormer","metrics":{"Mean F1":"92.8","Mean IoU":"86.8","Overall Accuracy":"91.3"},"uses_additional_data":true,"paper_date":"2021-09-18","paper":"/paper/efficient-hybrid-transformer-learning-global","paper_url":"https://arxiv.org/abs/2109.08937v4","paper_title":"UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagery","code":"https://github.com/WangLibo1995/GeoSeg","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":10,"model":"ABCNet","metrics":{"Overall Accuracy":"91.3"},"uses_additional_data":false,"paper_date":"2021-02-04","paper":"/paper/abcnet-attentive-bilateral-contextual-network","paper_url":"https://arxiv.org/abs/2102.02531v1","paper_title":"ABCNet: Attentive Bilateral Contextual Network for Efficient Semantic Segmentation of Fine-Resolution Remote Sensing Images","code":"https://github.com/lironui/ABCNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"ViTAE-B + RVSA -UperNet","metrics":{"Overall Accuracy":"91.22"},"uses_additional_data":true,"paper_date":"2022-08-08","paper":"/paper/advancing-plain-vision-transformer-towards","paper_url":"https://arxiv.org/abs/2208.03987v4","paper_title":"Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model","code":"https://github.com/vitae-transformer/vitae-transformer-remote-sensing","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"RSP-ViTAEv2-S-UperNet","metrics":{"Overall Accuracy":"91.21"},"uses_additional_data":true,"paper_date":"2022-04-06","paper":"/paper/an-empirical-study-of-remote-sensing","paper_url":"https://arxiv.org/abs/2204.02825v4","paper_title":"An Empirical Study of Remote Sensing Pretraining","code":"https://github.com/vitae-transformer/vitae-transformer-remote-sensing","n_code_links":2,"syntology":null},{"rank_in_archive_order":13,"model":"BANet","metrics":{"Overall Accuracy":"91.06"},"uses_additional_data":true,"paper_date":"2021-06-23","paper":"/paper/transformer-meets-convolution-a-bilateral","paper_url":"https://arxiv.org/abs/2106.12413v2","paper_title":"Transformer Meets Convolution: A Bilateral Awareness Network for Semantic Segmentation of Very Fine Resolution Urban Scene Images","code":"https://github.com/WangLibo1995/GeoSeg","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"RSP-Swin-T-UperNet","metrics":{"Overall Accuracy":"90.78"},"uses_additional_data":true,"paper_date":"2022-04-06","paper":"/paper/an-empirical-study-of-remote-sensing","paper_url":"https://arxiv.org/abs/2204.02825v4","paper_title":"An Empirical Study of Remote Sensing Pretraining","code":"https://github.com/vitae-transformer/vitae-transformer-remote-sensing","n_code_links":2,"syntology":null},{"rank_in_archive_order":15,"model":"ViT-B + RVSA-UperNet","metrics":{"Overall Accuracy":"90.77"},"uses_additional_data":true,"paper_date":"2022-08-08","paper":"/paper/advancing-plain-vision-transformer-towards","paper_url":"https://arxiv.org/abs/2208.03987v4","paper_title":"Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model","code":"https://github.com/vitae-transformer/vitae-transformer-remote-sensing","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"RSP-ResNet-50-UperNet","metrics":{"Overall Accuracy":"90.61"},"uses_additional_data":true,"paper_date":"2022-04-06","paper":"/paper/an-empirical-study-of-remote-sensing","paper_url":"https://arxiv.org/abs/2204.02825v4","paper_title":"An Empirical Study of Remote Sensing Pretraining","code":"https://github.com/vitae-transformer/vitae-transformer-remote-sensing","n_code_links":2,"syntology":null},{"rank_in_archive_order":17,"model":"PSPNet (SAP)","metrics":{"Mean IoU":"74.3","Overall Accuracy":"88.56"},"uses_additional_data":false,"paper_date":"2024-09-25","paper":"/paper/stochastic-subsampling-with-average-pooling","paper_url":"https://arxiv.org/abs/2409.16630v1","paper_title":"Stochastic Subsampling With Average Pooling","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":18,"model":"D2LS","metrics":{"Mean F1":"94.7"},"uses_additional_data":false,"paper_date":"2025-03-09","paper":"/paper/dynamic-dictionary-learning-for-remote","paper_url":"https://arxiv.org/abs/2503.06683v1","paper_title":"Dynamic Dictionary Learning for Remote Sensing Image Segmentation","code":"https://github.com/XavierJiezou/D2LS","n_code_links":1,"syntology":{"n_ran":9,"n_unverified":3,"n_samples":12,"n_pointer_only_licence":12}},{"rank_in_archive_order":19,"model":"SFA-Net","metrics":{"Mean F1":"93.5"},"uses_additional_data":false,"paper_date":"2024-09-03","paper":"/paper/sfa-net-semantic-feature-adjustment-network","paper_url":"https://www.mdpi.com/2072-4292/16/17/3278","paper_title":"SFA-Net: Semantic Feature Adjustment Network for Remote Sensing Image Segmentation","code":"https://github.com/j2jeong/priv","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"U-Net (ConvFormer-M36)","metrics":{"Mean IoU":"89.45"},"uses_additional_data":false,"paper_date":"2024-06-08","paper":"/paper/u-net-ensemble-for-enhanced-semantic","paper_url":"https://www.mdpi.com/2072-4292/16/12/2077","paper_title":"U-Net Ensemble for Enhanced Semantic Segmentation in Remote Sensing Imagery","code":null,"n_code_links":0,"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":6,"rows_with_any_sample_ran":6,"distinct_papers_with_graph_line":4,"distinct_papers_with_any_sample_ran":4,"samples_over_distinct_papers":{"n_ran":16,"n_unverified":4,"n_samples":20,"n_pointer_only_licence":16,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":21,"n_unverified":5,"n_samples":26,"n_pointer_only_licence":18,"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"}}}