{"url":"/sota/thermal-image-segmentation-on-rgb-t-glass","task":{"name":"Thermal Image Segmentation","url":"/task/thermal-image-segmentation","note":null},"dataset":{"name":"RGB-T-Glass-Segmentation","url":null},"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":["MAE"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"MAE":"lower"}},"counts":{"rows":22,"rows_with_code":20,"rows_with_paper_page":22,"rows_dated":21,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"RGB-T-Glass-Segmentation","metrics":{"MAE":"0.024"},"uses_additional_data":false,"paper_date":"2022-04-12","paper":"/paper/glass-segmentation-with-rgb-thermal-image","paper_url":"https://arxiv.org/abs/2204.05453v4","paper_title":"Glass Segmentation with RGB-Thermal Image Pairs","code":"https://github.com/dong-huo/rgb-t-glass-segmentation","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"CMX","metrics":{"MAE":"0.029"},"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":3,"model":"ESANet","metrics":{"MAE":"0.040"},"uses_additional_data":false,"paper_date":"2020-11-13","paper":"/paper/efficient-rgb-d-semantic-segmentation-for","paper_url":"https://arxiv.org/abs/2011.06961v3","paper_title":"Efficient RGB-D Semantic Segmentation for Indoor Scene Analysis","code":"https://github.com/TUI-NICR/ESANet","n_code_links":4,"syntology":null},{"rank_in_archive_order":4,"model":"EBS","metrics":{"MAE":"0.040"},"uses_additional_data":false,"paper_date":"2021-12-27","paper":"/paper/learning-generative-vision-transformer-with-1","paper_url":"https://arxiv.org/abs/2112.13528v1","paper_title":"Learning Generative Vision Transformer with Energy-Based Latent Space for Saliency Prediction","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":5,"model":"CLNet","metrics":{"MAE":"0.041"},"uses_additional_data":false,"paper_date":"2021-09-15","paper":"/paper/rgb-d-saliency-detection-via-cascaded-mutual","paper_url":"https://arxiv.org/abs/2109.07246v2","paper_title":"RGB-D Saliency Detection via Cascaded Mutual Information Minimization","code":"https://github.com/jingzhang617/cascaded_rgbd_sod","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":6,"model":"SPNet","metrics":{"MAE":"0.041"},"uses_additional_data":false,"paper_date":"2021-08-18","paper":"/paper/specificity-preserving-rgb-d-saliency","paper_url":"https://arxiv.org/abs/2108.08162v2","paper_title":"Specificity-preserving RGB-D Saliency Detection","code":"https://github.com/taozh2017/RGBD-SODsurvey","n_code_links":3,"syntology":{"n_ran":8,"n_unverified":6,"n_samples":14,"n_pointer_only_licence":14}},{"rank_in_archive_order":7,"model":"VST","metrics":{"MAE":"0.044"},"uses_additional_data":false,"paper_date":"2021-04-25","paper":"/paper/visual-saliency-transformer","paper_url":"https://arxiv.org/abs/2104.12099v2","paper_title":"Visual Saliency Transformer","code":"https://github.com/nnizhang/VST","n_code_links":2,"syntology":{"n_ran":7,"n_unverified":4,"n_samples":11,"n_pointer_only_licence":11}},{"rank_in_archive_order":8,"model":"RD3D","metrics":{"MAE":"0.045"},"uses_additional_data":false,"paper_date":"2021-01-25","paper":"/paper/rgb-d-salient-object-detection-via-3d","paper_url":"https://arxiv.org/abs/2101.10241v1","paper_title":"RGB-D Salient Object Detection via 3D Convolutional Neural Networks","code":"https://github.com/PPOLYpubki/RD3D","n_code_links":1,"syntology":{"n_ran":9,"n_unverified":4,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":9,"model":"HDFNet","metrics":{"MAE":"0.048"},"uses_additional_data":false,"paper_date":"2020-07-13","paper":"/paper/hierarchical-dynamic-filtering-network-for","paper_url":"https://arxiv.org/abs/2007.06227v3","paper_title":"Hierarchical Dynamic Filtering Network for RGB-D Salient Object Detection","code":"https://github.com/lartpang/HDFNet","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":4,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"UTA","metrics":{"MAE":"0.052"},"uses_additional_data":false,"paper_date":"2021-09-08","paper":"/paper/rgb-d-salient-object-detection-with","paper_url":"https://arxiv.org/abs/2109.03425v1","paper_title":"RGB-D Salient Object Detection with Ubiquitous Target Awareness","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"SegFormer","metrics":{"MAE":"0.053"},"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":"ShapeConv","metrics":{"MAE":"0.054"},"uses_additional_data":false,"paper_date":"2021-08-24","paper":"/paper/shapeconv-shape-aware-convolutional-layer-for","paper_url":"https://arxiv.org/abs/2108.10528v1","paper_title":"ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation","code":"https://github.com/hanchaoleng/shapeconv","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":4,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":13,"model":"DCFNet","metrics":{"MAE":"0.056"},"uses_additional_data":false,"paper_date":"2021-06-19","paper":"/paper/calibrated-rgb-d-salient-object-detection","paper_url":"http://openaccess.thecvf.com//content/CVPR2021/html/Ji_Calibrated_RGB-D_Salient_Object_Detection_CVPR_2021_paper.html","paper_title":"Calibrated RGB-D Salient Object Detection","code":"https://github.com/jiwei0921/DCF","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"RTFNet","metrics":{"MAE":"0.058"},"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":15,"model":"DANet","metrics":{"MAE":"0.069"},"uses_additional_data":false,"paper_date":"2020-07-14","paper":"/paper/a-single-stream-network-for-robust-and-real","paper_url":"https://arxiv.org/abs/2007.06811v2","paper_title":"A Single Stream Network for Robust and Real-time RGB-D Salient Object Detection","code":"https://github.com/Xiaoqi-Zhao-DLUT/DANet-RGBD-Saliency","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"UCNet","metrics":{"MAE":"0.071"},"uses_additional_data":false,"paper_date":"2020-04-13","paper":"/paper/uc-net-uncertainty-inspired-rgb-d-saliency","paper_url":"https://arxiv.org/abs/2004.05763v1","paper_title":"UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders","code":"https://github.com/JingZhang617/UCNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":17,"model":"Segmenter","metrics":{"MAE":"0.072"},"uses_additional_data":false,"paper_date":"2021-05-12","paper":"/paper/segmenter-transformer-for-semantic","paper_url":"https://arxiv.org/abs/2105.05633v3","paper_title":"Segmenter: Transformer for Semantic Segmentation","code":"https://github.com/PaddlePaddle/PaddleSeg","n_code_links":8,"syntology":{"n_ran":0,"n_unverified":7,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":18,"model":"SSF","metrics":{"MAE":"0.097"},"uses_additional_data":false,"paper_date":"2020-06-01","paper":"/paper/select-supplement-and-focus-for-rgb-d","paper_url":"http://openaccess.thecvf.com/content_CVPR_2020/html/Zhang_Select_Supplement_and_Focus_for_RGB-D_Saliency_Detection_CVPR_2020_paper.html","paper_title":"Select, Supplement and Focus for RGB-D Saliency Detection","code":"https://github.com/OIPLab-DUT/CVPR_SSF-RGBD","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"ATSA","metrics":{"MAE":"0.098"},"uses_additional_data":false,"paper_date":null,"paper":"/paper/asymmetric-two-stream-architecture-for","paper_url":"https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/6188_ECCV_2020_paper.php","paper_title":"Asymmetric Two-Stream Architecture for Accurate RGB-D Saliency Detection","code":"https://github.com/OIPLab-DUT/ATSA","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"EBLNet","metrics":{"MAE":"0.104"},"uses_additional_data":false,"paper_date":"2021-03-29","paper":"/paper/enhanced-boundary-learning-for-glass-like","paper_url":"https://arxiv.org/abs/2103.15734v2","paper_title":"Enhanced Boundary Learning for Glass-like Object Segmentation","code":"https://github.com/hehao13/EBLNet","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":4}},{"rank_in_archive_order":21,"model":"CoNet","metrics":{"MAE":"0.145"},"uses_additional_data":false,"paper_date":"2020-07-23","paper":"/paper/accurate-rgb-d-salient-object-detection-via","paper_url":"https://arxiv.org/abs/2007.11782v1","paper_title":"Accurate RGB-D Salient Object Detection via Collaborative Learning","code":"https://github.com/jiwei0921/CoNet","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":22,"model":"DPANet","metrics":{"MAE":"0.154"},"uses_additional_data":false,"paper_date":"2020-03-19","paper":"/paper/depth-potentiality-aware-gated-attention","paper_url":"https://arxiv.org/abs/2003.08608v4","paper_title":"DPANet: Depth Potentiality-Aware Gated Attention Network for RGB-D Salient Object Detection","code":"https://github.com/JosephChenHub/DPANet","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":6,"n_samples":8,"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 6,264 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":13,"rows_with_any_sample_ran":10,"distinct_papers_with_graph_line":13,"distinct_papers_with_any_sample_ran":10,"samples_over_distinct_papers":{"n_ran":86,"n_unverified":77,"n_samples":163,"n_pointer_only_licence":47,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":86,"n_unverified":77,"n_samples":163,"n_pointer_only_licence":47,"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"}}}