{"url":"/sota/semantic-segmentation-on-vaihingen","task":{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","note":null},"dataset":{"name":"Vaihingen","url":null},"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":["mIoU"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"mIoU":null}},"counts":{"rows":13,"rows_with_code":12,"rows_with_paper_page":13,"rows_dated":13,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"CMX","metrics":{"mIoU":"82.87"},"uses_additional_data":false,"paper_date":"2022-03-09","paper":"/paper/cmx-cross-modal-fusion-for-rgb-x-semantic","paper_url":"https://arxiv.org/abs/2203.04838v5","paper_title":"CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers","code":"https://github.com/huaaaliu/rgbx_semantic_segmentation","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"LMFNet-2 (","metrics":{"mIoU":"82.49"},"uses_additional_data":false,"paper_date":"2024-04-21","paper":"/paper/lmfnet-an-efficient-multimodal-fusion","paper_url":"https://arxiv.org/abs/2404.13659v1","paper_title":"LMFNet: An Efficient Multimodal Fusion Approach for Semantic Segmentation in High-Resolution Remote Sensing","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"SA-Gate","metrics":{"mIoU":"81.03"},"uses_additional_data":false,"paper_date":"2020-07-17","paper":"/paper/bi-directional-cross-modality-feature","paper_url":"https://arxiv.org/abs/2007.09183v1","paper_title":"Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation","code":"https://github.com/charlesCXK/RGBD_Semantic_Segmentation_PyTorch","n_code_links":2,"syntology":null},{"rank_in_archive_order":4,"model":"V-FuseNet","metrics":{"mIoU":"79.56"},"uses_additional_data":false,"paper_date":"2017-11-23","paper":"/paper/beyond-rgb-very-high-resolution-urban-remote","paper_url":"http://arxiv.org/abs/1711.08681v1","paper_title":"Beyond RGB: Very High Resolution Urban Remote Sensing With Multimodal Deep Networks","code":"https://github.com/nshaud/DeepNetsForEO","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"UnetFormer","metrics":{"mIoU":"77.24"},"uses_additional_data":false,"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":6,"model":"SegFormer-B1","metrics":{"mIoU":"76.92"},"uses_additional_data":false,"paper_date":"2021-05-31","paper":"/paper/segformer-simple-and-efficient-design-for","paper_url":"https://arxiv.org/abs/2105.15203v3","paper_title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","code":"https://github.com/huggingface/transformers","n_code_links":28,"syntology":{"n_ran":48,"n_unverified":38,"n_samples":86,"n_pointer_only_licence":15}},{"rank_in_archive_order":7,"model":"PSPNet","metrics":{"mIoU":"76.79"},"uses_additional_data":false,"paper_date":"2016-12-04","paper":"/paper/pyramid-scene-parsing-network","paper_url":"http://arxiv.org/abs/1612.01105v2","paper_title":"Pyramid Scene Parsing Network","code":"https://github.com/tensorflow/models","n_code_links":67,"syntology":{"n_ran":7,"n_unverified":22,"n_samples":29,"n_pointer_only_licence":5}},{"rank_in_archive_order":8,"model":"HRNet-48","metrics":{"mIoU":"76.75"},"uses_additional_data":false,"paper_date":"2019-08-20","paper":"/paper/190807919","paper_url":"https://arxiv.org/abs/1908.07919v2","paper_title":"Deep High-Resolution Representation Learning for Visual Recognition","code":"https://github.com/open-mmlab/mmdetection","n_code_links":42,"syntology":{"n_ran":3,"n_unverified":31,"n_samples":34,"n_pointer_only_licence":16}},{"rank_in_archive_order":9,"model":"SegFormer-B2","metrics":{"mIoU":"76.69"},"uses_additional_data":false,"paper_date":"2021-05-31","paper":"/paper/segformer-simple-and-efficient-design-for","paper_url":"https://arxiv.org/abs/2105.15203v3","paper_title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","code":"https://github.com/huggingface/transformers","n_code_links":28,"syntology":{"n_ran":48,"n_unverified":38,"n_samples":86,"n_pointer_only_licence":15}},{"rank_in_archive_order":10,"model":"HRNet-18","metrics":{"mIoU":"75.90"},"uses_additional_data":false,"paper_date":"2019-08-20","paper":"/paper/190807919","paper_url":"https://arxiv.org/abs/1908.07919v2","paper_title":"Deep High-Resolution Representation Learning for Visual Recognition","code":"https://github.com/open-mmlab/mmdetection","n_code_links":42,"syntology":{"n_ran":3,"n_unverified":31,"n_samples":34,"n_pointer_only_licence":16}},{"rank_in_archive_order":11,"model":"SegFormer-B0","metrics":{"mIoU":"75.57"},"uses_additional_data":false,"paper_date":"2021-05-31","paper":"/paper/segformer-simple-and-efficient-design-for","paper_url":"https://arxiv.org/abs/2105.15203v3","paper_title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","code":"https://github.com/huggingface/transformers","n_code_links":28,"syntology":{"n_ran":48,"n_unverified":38,"n_samples":86,"n_pointer_only_licence":15}},{"rank_in_archive_order":12,"model":"FPN","metrics":{"mIoU":"74.86"},"uses_additional_data":false,"paper_date":"2016-12-09","paper":"/paper/feature-pyramid-networks-for-object-detection","paper_url":"http://arxiv.org/abs/1612.03144v2","paper_title":"Feature Pyramid Networks for Object Detection","code":"https://github.com/PaddlePaddle/PaddleOCR","n_code_links":85,"syntology":{"n_ran":16,"n_unverified":35,"n_samples":51,"n_pointer_only_licence":11}},{"rank_in_archive_order":13,"model":"DeepLabV3+","metrics":{"mIoU":"72.90"},"uses_additional_data":false,"paper_date":"2018-02-07","paper":"/paper/encoder-decoder-with-atrous-separable","paper_url":"http://arxiv.org/abs/1802.02611v3","paper_title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","code":"https://github.com/tensorflow/models/tree/master/research/deeplab","n_code_links":78,"syntology":{"n_ran":43,"n_unverified":29,"n_samples":72,"n_pointer_only_licence":40}}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"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":10,"rows_with_any_sample_ran":10,"distinct_papers_with_graph_line":7,"distinct_papers_with_any_sample_ran":7,"samples_over_distinct_papers":{"n_ran":121,"n_unverified":155,"n_samples":276,"n_pointer_only_licence":89,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":220,"n_unverified":262,"n_samples":482,"n_pointer_only_licence":135,"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"}}}