{"url":"/sota/semantic-segmentation-on-mcubes","task":{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","note":null},"dataset":{"name":"MCubeS","url":"/dataset/mcubes"},"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":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":"StitchFusion (RGB-A-D-N)","metrics":{"mIoU":"53.92"},"uses_additional_data":false,"paper_date":"2024-08-02","paper":"/paper/2408-01343","paper_url":"https://arxiv.org/abs/2408.01343v1","paper_title":"StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentation","code":"https://github.com/libingyu01/stitchfusion-stitchfusion-weaving-any-visual-modalities-to-enhance-multimodal-semantic-segmentation","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"StitchFusion (RGB-A-D)","metrics":{"mIoU":"53.26"},"uses_additional_data":false,"paper_date":"2024-08-02","paper":"/paper/2408-01343","paper_url":"https://arxiv.org/abs/2408.01343v1","paper_title":"StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentation","code":"https://github.com/libingyu01/stitchfusion-stitchfusion-weaving-any-visual-modalities-to-enhance-multimodal-semantic-segmentation","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"StitchFusion (RGB-N)","metrics":{"mIoU":"53.21"},"uses_additional_data":false,"paper_date":"2024-08-02","paper":"/paper/2408-01343","paper_url":"https://arxiv.org/abs/2408.01343v1","paper_title":"StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentation","code":"https://github.com/libingyu01/stitchfusion-stitchfusion-weaving-any-visual-modalities-to-enhance-multimodal-semantic-segmentation","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"MMSFormer (RGB-A-D-N)","metrics":{"mIoU":"53.11%"},"uses_additional_data":false,"paper_date":"2023-09-07","paper":"/paper/multimodal-transformer-for-material","paper_url":"https://arxiv.org/abs/2309.04001v4","paper_title":"MMSFormer: Multimodal Transformer for Material and Semantic Segmentation","code":"https://github.com/csiplab/mmsformer","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"MemorySAM-B+(RGB-A-D-N)","metrics":{"mIoU":"52.88"},"uses_additional_data":false,"paper_date":"2025-03-09","paper":"/paper/memorysam-memorize-modalities-and-semantics","paper_url":"https://arxiv.org/abs/2503.06700v1","paper_title":"MemorySAM: Memorize Modalities and Semantics with Segment Anything Model 2 for Multi-modal Semantic Segmentation","code":"https://github.com/Chenfei-Liao/MemorySAM","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"StitchFusion (RGB-D)","metrics":{"mIoU":"52.72"},"uses_additional_data":false,"paper_date":"2024-08-02","paper":"/paper/2408-01343","paper_url":"https://arxiv.org/abs/2408.01343v1","paper_title":"StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentation","code":"https://github.com/libingyu01/stitchfusion-stitchfusion-weaving-any-visual-modalities-to-enhance-multimodal-semantic-segmentation","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"StitchFusion (RGB-A)","metrics":{"mIoU":"52.68"},"uses_additional_data":false,"paper_date":"2024-08-02","paper":"/paper/2408-01343","paper_url":"https://arxiv.org/abs/2408.01343v1","paper_title":"StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentation","code":"https://github.com/libingyu01/stitchfusion-stitchfusion-weaving-any-visual-modalities-to-enhance-multimodal-semantic-segmentation","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"MemorySAM-B+(RGB-A-D)","metrics":{"mIoU":"52.20"},"uses_additional_data":false,"paper_date":"2025-03-09","paper":"/paper/memorysam-memorize-modalities-and-semantics","paper_url":"https://arxiv.org/abs/2503.06700v1","paper_title":"MemorySAM: Memorize Modalities and Semantics with Segment Anything Model 2 for Multi-modal Semantic Segmentation","code":"https://github.com/Chenfei-Liao/MemorySAM","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"MMSFormer (RGB-A-D)","metrics":{"mIoU":"52.05%"},"uses_additional_data":false,"paper_date":"2023-09-07","paper":"/paper/multimodal-transformer-for-material","paper_url":"https://arxiv.org/abs/2309.04001v4","paper_title":"MMSFormer: Multimodal Transformer for Material and Semantic Segmentation","code":"https://github.com/csiplab/mmsformer","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"CMNeXt (B2 RGB-A-D-N)","metrics":{"mIoU":"51.54%"},"uses_additional_data":false,"paper_date":"2023-03-02","paper":"/paper/delivering-arbitrary-modal-semantic","paper_url":"https://arxiv.org/abs/2303.01480v1","paper_title":"Delivering Arbitrary-Modal Semantic Segmentation","code":"https://github.com/jamycheung/DELIVER","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"MMSFormer (RGB-A)","metrics":{"mIoU":"51.30%"},"uses_additional_data":false,"paper_date":"2023-09-07","paper":"/paper/multimodal-transformer-for-material","paper_url":"https://arxiv.org/abs/2309.04001v4","paper_title":"MMSFormer: Multimodal Transformer for Material and Semantic Segmentation","code":"https://github.com/csiplab/mmsformer","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"MemorySAM-B+(RGB-A)","metrics":{"mIoU":"51.20"},"uses_additional_data":false,"paper_date":"2025-03-09","paper":"/paper/memorysam-memorize-modalities-and-semantics","paper_url":"https://arxiv.org/abs/2503.06700v1","paper_title":"MemorySAM: Memorize Modalities and Semantics with Segment Anything Model 2 for Multi-modal Semantic Segmentation","code":"https://github.com/Chenfei-Liao/MemorySAM","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"ShareCMP (B2 RGB-A-D)","metrics":{"mIoU":"50.99%"},"uses_additional_data":false,"paper_date":"2023-12-06","paper":"/paper/sharecmp-polarization-aware-rgb-p-semantic","paper_url":"https://arxiv.org/abs/2312.03430v2","paper_title":"ShareCMP: Polarization-Aware RGB-P Semantic Segmentation","code":"https://github.com/lefteyex/sharecmp","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"ShareCMP(B2 RGB-D)","metrics":{"mIoU":"50.55"},"uses_additional_data":false,"paper_date":"2023-12-06","paper":"/paper/sharecmp-polarization-aware-rgb-p-semantic","paper_url":"https://arxiv.org/abs/2312.03430v2","paper_title":"ShareCMP: Polarization-Aware RGB-P Semantic Segmentation","code":"https://github.com/lefteyex/sharecmp","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"MMSFormer (RGB)","metrics":{"mIoU":"50.44%"},"uses_additional_data":false,"paper_date":"2023-09-07","paper":"/paper/multimodal-transformer-for-material","paper_url":"https://arxiv.org/abs/2309.04001v4","paper_title":"MMSFormer: Multimodal Transformer for Material and Semantic Segmentation","code":"https://github.com/csiplab/mmsformer","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"ShareCMP(B2 RGB-A)","metrics":{"mIoU":"50.34"},"uses_additional_data":false,"paper_date":"2023-12-06","paper":"/paper/sharecmp-polarization-aware-rgb-p-semantic","paper_url":"https://arxiv.org/abs/2312.03430v2","paper_title":"ShareCMP: Polarization-Aware RGB-P Semantic Segmentation","code":"https://github.com/lefteyex/sharecmp","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":17,"model":"CMNeXt (B2 RGB-A-D)","metrics":{"mIoU":"49.48%"},"uses_additional_data":false,"paper_date":"2023-03-02","paper":"/paper/delivering-arbitrary-modal-semantic","paper_url":"https://arxiv.org/abs/2303.01480v1","paper_title":"Delivering Arbitrary-Modal Semantic Segmentation","code":"https://github.com/jamycheung/DELIVER","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":18,"model":"CMNeXt (B2 RGB-A)","metrics":{"mIoU":"48.42%"},"uses_additional_data":false,"paper_date":"2023-03-02","paper":"/paper/delivering-arbitrary-modal-semantic","paper_url":"https://arxiv.org/abs/2303.01480v1","paper_title":"Delivering Arbitrary-Modal Semantic Segmentation","code":"https://github.com/jamycheung/DELIVER","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":19,"model":"MCubeSNet (RGB-A-D-N)","metrics":{"mIoU":"42.86%"},"uses_additional_data":false,"paper_date":"2022-01-01","paper":"/paper/multimodal-material-segmentation","paper_url":"http://openaccess.thecvf.com//content/CVPR2022/html/Liang_Multimodal_Material_Segmentation_CVPR_2022_paper.html","paper_title":"Multimodal Material Segmentation","code":"https://github.com/kyotovision-public/multimodal-material-segmentation","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"DeepLabV3+ (RGB-A-D-N)","metrics":{"mIoU":"38.13%"},"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}},{"rank_in_archive_order":21,"model":"DDF (RGB-A-D-N)","metrics":{"mIoU":"36.16%"},"uses_additional_data":false,"paper_date":"2021-04-29","paper":"/paper/decoupled-dynamic-filter-networks","paper_url":"https://arxiv.org/abs/2104.14107v1","paper_title":"Decoupled Dynamic Filter Networks","code":"https://github.com/theFoxofSky/ddf","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":22,"model":"DRConv (RGB-A-D-N)","metrics":{"mIoU":"34.63%"},"uses_additional_data":false,"paper_date":"2020-03-27","paper":"/paper/dynamic-region-aware-convolution","paper_url":"https://arxiv.org/abs/2003.12243v3","paper_title":"Dynamic Region-Aware Convolution","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 6,795 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":6795,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2785},"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":8,"rows_with_any_sample_ran":8,"distinct_papers_with_graph_line":4,"distinct_papers_with_any_sample_ran":4,"samples_over_distinct_papers":{"n_ran":54,"n_unverified":30,"n_samples":84,"n_pointer_only_licence":40,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":72,"n_unverified":32,"n_samples":104,"n_pointer_only_licence":40,"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"}}}