{"url":"/sota/semantic-segmentation-on-fmb-dataset","task":{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","note":null},"dataset":{"name":"FMB Dataset","url":"/dataset/fmb-dataset"},"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":14,"rows_with_code":12,"rows_with_paper_page":14,"rows_dated":14,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"RoadFormer+ (RGB-Infrared)","metrics":{"mIoU":"73.1"},"uses_additional_data":false,"paper_date":"2024-07-31","paper":"/paper/roadformer-delivering-rgb-x-scene-parsing","paper_url":"https://arxiv.org/abs/2407.21631v2","paper_title":"RoadFormer+: Delivering RGB-X Scene Parsing through Scale-Aware Information Decoupling and Advanced Heterogeneous Feature Fusion","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"SHIFNet (RGB-Infrared)","metrics":{"mIoU":"67.8"},"uses_additional_data":false,"paper_date":"2025-03-04","paper":"/paper/unveiling-the-potential-of-segment-anything","paper_url":"https://arxiv.org/abs/2503.02581v1","paper_title":"Unveiling the Potential of Segment Anything Model 2 for RGB-Thermal Semantic Segmentation with Language Guidance","code":"https://github.com/iasakit3t/shifnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"StitchFusion+FFMs (RGB-Infrared)","metrics":{"mIoU":"64.32"},"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":"StitchFusion (RGB-Infrared)","metrics":{"mIoU":"63.30"},"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":5,"model":"MMSFormer (RGB-Infrared)","metrics":{"mIoU":"61.70"},"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":6,"model":"MMSFormer (RGB)","metrics":{"mIoU":"57.20"},"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":7,"model":"SegMiF (RGB-Infrared)","metrics":{"mIoU":"54.80"},"uses_additional_data":false,"paper_date":"2023-08-04","paper":"/paper/multi-interactive-feature-learning-and-a-full","paper_url":"https://arxiv.org/abs/2308.02097v1","paper_title":"Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation","code":"https://github.com/jinyuanliu-cv/segmif","n_code_links":2,"syntology":{"n_ran":19,"n_unverified":7,"n_samples":26,"n_pointer_only_licence":13}},{"rank_in_archive_order":8,"model":"ReCoNet (RGB-Infrared)","metrics":{"mIoU":"50.90"},"uses_additional_data":false,"paper_date":"2018-07-03","paper":"/paper/reconet-real-time-coherent-video-style","paper_url":"http://arxiv.org/abs/1807.01197v2","paper_title":"ReCoNet: Real-time Coherent Video Style Transfer Network","code":"https://github.com/safwankdb/ReCoNet-PyTorch","n_code_links":8,"syntology":null},{"rank_in_archive_order":9,"model":"DIDFuse (RGB-Infrared)","metrics":{"mIoU":"50.60"},"uses_additional_data":false,"paper_date":"2020-03-20","paper":"/paper/didfuse-deep-image-decomposition-for-infrared","paper_url":"https://arxiv.org/abs/2003.09210v3","paper_title":"DIDFuse: Deep Image Decomposition for Infrared and Visible Image Fusion","code":"https://github.com/Zhaozixiang1228/IVIF-DIDFuse","n_code_links":2,"syntology":{"n_ran":6,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":7}},{"rank_in_archive_order":10,"model":"SegMiF (RGB)","metrics":{"mIoU":"50.50"},"uses_additional_data":false,"paper_date":"2023-08-04","paper":"/paper/multi-interactive-feature-learning-and-a-full","paper_url":"https://arxiv.org/abs/2308.02097v1","paper_title":"Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation","code":"https://github.com/jinyuanliu-cv/segmif","n_code_links":2,"syntology":{"n_ran":19,"n_unverified":7,"n_samples":26,"n_pointer_only_licence":13}},{"rank_in_archive_order":11,"model":"GMNet (RGB-Infrared)","metrics":{"mIoU":"49.20"},"uses_additional_data":false,"paper_date":"2020-07-17","paper":"/paper/gmnet-graph-matching-network-for-large-scale","paper_url":"https://arxiv.org/abs/2007.09073v1","paper_title":"GMNet: Graph Matching Network for Large Scale Part Semantic Segmentation in the Wild","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"TarDAL (RGB-Infrared)","metrics":{"mIoU":"48.10"},"uses_additional_data":false,"paper_date":"2022-03-30","paper":"/paper/target-aware-dual-adversarial-learning-and-a","paper_url":"https://arxiv.org/abs/2203.16220v1","paper_title":"Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection","code":"https://github.com/JinyuanLiu-CV/TarDAL","n_code_links":2,"syntology":null},{"rank_in_archive_order":13,"model":"EGFNet (RGB-Infrared)","metrics":{"mIoU":"47.30"},"uses_additional_data":false,"paper_date":"2023-08-15","paper":"/paper/egfnet-edge-aware-guidance-fusion-network-for","paper_url":"https://ieeexplore.ieee.org/abstract/document/10234530","paper_title":"EGFNet: Edge-Aware Guidance Fusion Network for RGB–Thermal Urban Scene Parsing","code":"https://github.com/shaohuadong2021/egfnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"FEANet (RGB-Infrared)","metrics":{"mIoU":"46.80"},"uses_additional_data":false,"paper_date":"2021-10-18","paper":"/paper/feanet-feature-enhanced-attention-network-for","paper_url":"https://arxiv.org/abs/2110.08988v1","paper_title":"FEANet: Feature-Enhanced Attention Network for RGB-Thermal Real-time Semantic Segmentation","code":"https://github.com/matrixgame2018/FEANet","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":0}}],"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 6,821 of the 9,623 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":9623,"papers_checked":6821,"papers_extracted_not_yet_verified":65,"boards_without_verdict":29,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+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":4,"rows_with_any_sample_ran":4,"distinct_papers_with_graph_line":3,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":29,"n_unverified":9,"n_samples":38,"n_pointer_only_licence":20,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":48,"n_unverified":16,"n_samples":64,"n_pointer_only_licence":33,"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"}}}