{"url":"/sota/thermal-image-segmentation-on-pst900","task":{"name":"Thermal Image Segmentation","url":"/task/thermal-image-segmentation","note":null},"dataset":{"name":"PST900","url":"/dataset/pst900"},"category":"Computer Vision","categories":["Computer Vision","Methodology"],"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":17,"rows_with_paper_page":22,"rows_dated":22,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"SHIFNet","metrics":{"mIoU":"89.8"},"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":2,"model":"HAPNet","metrics":{"mIoU":"89.0"},"uses_additional_data":false,"paper_date":"2024-04-04","paper":"/paper/hapnet-toward-superior-rgb-thermal-scene","paper_url":"https://arxiv.org/abs/2404.03527v2","paper_title":"HAPNet: Toward Superior RGB-Thermal Scene Parsing via Hybrid, Asymmetric, and Progressive Heterogeneous Feature Fusion","code":"https://github.com/LiJiahang617/HAPNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"CRM_RGBTSeg","metrics":{"mIoU":"88"},"uses_additional_data":false,"paper_date":"2023-03-30","paper":"/paper/complementary-random-masking-for-rgb-thermal","paper_url":"https://arxiv.org/abs/2303.17386v2","paper_title":"Complementary Random Masking for RGB-Thermal Semantic Segmentation","code":"https://github.com/UkcheolShin/CRM_RGBTSeg","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":5,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"Sigma-small","metrics":{"mIoU":"87.8"},"uses_additional_data":false,"paper_date":"2024-04-05","paper":"/paper/sigma-siamese-mamba-network-for-multi-modal","paper_url":"https://arxiv.org/abs/2404.04256v2","paper_title":"Sigma: Siamese Mamba Network for Multi-Modal Semantic Segmentation","code":"https://github.com/zifuwan/sigma","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"MMSFormer","metrics":{"mIoU":"87.45"},"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":"DPLNet","metrics":{"mIoU":"86.7"},"uses_additional_data":false,"paper_date":"2023-12-01","paper":"/paper/efficient-multimodal-semantic-segmentation","paper_url":"https://arxiv.org/abs/2312.00360v2","paper_title":"Efficient Multimodal Semantic Segmentation via Dual-Prompt Learning","code":"https://github.com/shaohuadong2021/dplnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"CACFNet","metrics":{"mIoU":"86.56"},"uses_additional_data":false,"paper_date":"2023-09-14","paper":"/paper/cacfnet-cross-modal-attention-cascaded-fusion","paper_url":"https://ieeexplore.ieee.org/abstract/document/10251592","paper_title":"CACFNet: Cross-Modal Attention Cascaded Fusion Network for RGB-T Urban Scene Parsing","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":8,"model":"EGFNet (ConvNeXt)","metrics":{"mIoU":"85.42"},"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":9,"model":"StitchFusion (RGB-T)","metrics":{"mIoU":"85.35"},"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":10,"model":"CAINet (MobileNet-V2)","metrics":{"mIoU":"84.74"},"uses_additional_data":false,"paper_date":"2024-01-03","paper":"/paper/context-aware-interaction-network-for-rgb-t","paper_url":"https://arxiv.org/abs/2401.01624v1","paper_title":"Context-Aware Interaction Network for RGB-T Semantic Segmentation","code":"https://github.com/yinglv1106/cainet","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"UniRGB-IR","metrics":{"mIoU":"82.8"},"uses_additional_data":false,"paper_date":"2024-04-26","paper":"/paper/unirgb-ir-a-unified-framework-for-visible","paper_url":"https://arxiv.org/abs/2404.17360v2","paper_title":"UniRGB-IR: A Unified Framework for RGB-Infrared Semantic Tasks via Adapter Tuning","code":"https://github.com/potsui99/unirgb-ir","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"SpiderMesh","metrics":{"mIoU":"82.3"},"uses_additional_data":false,"paper_date":"2023-03-15","paper":"/paper/spidermesh-spatial-aware-demand-guided","paper_url":"https://arxiv.org/abs/2303.08692v2","paper_title":"SpiderMesh: Spatial-aware Demand-guided Recursive Meshing for RGB-T Semantic Segmentation","code":"https://github.com/leofansq/spidermesh","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":13,"model":"GEBNet","metrics":{"mIoU":"81.15"},"uses_additional_data":false,"paper_date":"2022-10-31","paper":"/paper/gebnet-graph-enhancement-branch-network-for","paper_url":"https://ieeexplore.ieee.org/abstract/document/9937048","paper_title":"GEBNet: Graph-Enhancement Branch Network for RGB-T Scene Parsing","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":14,"model":"MTANet","metrics":{"mIoU":"78.60"},"uses_additional_data":false,"paper_date":"2022-04-05","paper":"/paper/mtanet-multitask-aware-network-with","paper_url":"https://ieeexplore.ieee.org/abstract/document/9749834","paper_title":"MTANet: Multitask-Aware Network With Hierarchical Multimodal Fusion for RGB-T Urban Scene Understanding","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":15,"model":"EGFNet","metrics":{"mIoU":"78.51"},"uses_additional_data":false,"paper_date":"2021-12-09","paper":"/paper/edge-aware-guidance-fusion-network-for-rgb","paper_url":"https://arxiv.org/abs/2112.05144v1","paper_title":"Edge-aware Guidance Fusion Network for RGB Thermal Scene Parsing","code":"https://github.com/shaohuadong2021/egfnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"CSRPNet (ResNet-50)","metrics":{"mIoU":"75.0"},"uses_additional_data":false,"paper_date":"2023-08-24","paper":"/paper/channel-and-spatial-relation-propagation","paper_url":"https://arxiv.org/abs/2308.12534v1","paper_title":"Channel and Spatial Relation-Propagation Network for RGB-Thermal Semantic Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":17,"model":"ACNet","metrics":{"mIoU":"71.81"},"uses_additional_data":false,"paper_date":"2019-05-24","paper":"/paper/acnet-attention-based-network-to-exploit","paper_url":"https://arxiv.org/abs/1905.10089v1","paper_title":"ACNet: Attention Based Network to Exploit Complementary Features for RGBD Semantic Segmentation","code":"https://github.com/anheidelonghu/ACNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"PSTNet","metrics":{"mIoU":"68.4"},"uses_additional_data":false,"paper_date":"2019-09-20","paper":"/paper/pst900-rgb-thermal-calibration-dataset-and","paper_url":"https://arxiv.org/abs/1909.10980v1","paper_title":"PST900: RGB-Thermal Calibration, Dataset and Segmentation Network","code":"https://github.com/ShreyasSkandanS/pst900_thermal_rgb","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"RTFNet","metrics":{"mIoU":"57.6"},"uses_additional_data":false,"paper_date":"2019-03-13","paper":"/paper/rtfnet-rgb-thermal-fusion-network-for","paper_url":"https://ieeexplore.ieee.org/abstract/document/8666745","paper_title":"RTFNet: RGB-Thermal Fusion Network for Semantic Segmentation of Urban Scenes","code":"https://github.com/yuxiangsun/RTFNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"MFNet","metrics":{"mIoU":"57.0"},"uses_additional_data":false,"paper_date":"2017-12-14","paper":"/paper/mfnet-towards-real-time-semantic-segmentation","paper_url":"https://ieeexplore.ieee.org/abstract/document/8206396","paper_title":"MFNet: Towards real-time semantic segmentation for autonomous vehicles with multi-spectral scenes","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":21,"model":"UNet","metrics":{"mIoU":"52.8"},"uses_additional_data":false,"paper_date":"2015-05-18","paper":"/paper/u-net-convolutional-networks-for-biomedical","paper_url":"http://arxiv.org/abs/1505.04597v1","paper_title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","code":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","n_code_links":487,"syntology":{"n_ran":518,"n_unverified":239,"n_samples":757,"n_pointer_only_licence":426}},{"rank_in_archive_order":22,"model":"Fast-SCNN","metrics":{"mIoU":"47.2"},"uses_additional_data":false,"paper_date":"2019-02-12","paper":"/paper/fast-scnn-fast-semantic-segmentation-network","paper_url":"http://arxiv.org/abs/1902.04502v1","paper_title":"Fast-SCNN: Fast Semantic Segmentation Network","code":"https://github.com/open-mmlab/mmsegmentation","n_code_links":24,"syntology":{"n_ran":21,"n_unverified":11,"n_samples":32,"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 7,081 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":7081,"papers_extracted_not_yet_verified":217,"boards_without_verdict":27,"papers_not_yet_extracted":2325},"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":5,"rows_with_any_sample_ran":4,"distinct_papers_with_graph_line":5,"distinct_papers_with_any_sample_ran":4,"samples_over_distinct_papers":{"n_ran":542,"n_unverified":257,"n_samples":799,"n_pointer_only_licence":427,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":542,"n_unverified":257,"n_samples":799,"n_pointer_only_licence":427,"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"}}}