{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/sota/semantic-segmentation-on-nyu-depth-v2","task":{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","note":null},"dataset":{"name":"NYU Depth v2","url":"/dataset/nyuv2"},"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":["Mean IoU","Mean Accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction; the tokens 'score' and 'time' are not used on this page); null = not inferred, chart draws points only","by_metric":{"Mean IoU":"higher","Mean Accuracy":"higher"}},"counts":{"rows":121,"rows_with_code":86,"rows_with_paper_page":121,"rows_dated":121,"rows_using_additional_data":5},"rows":[{"rank_in_archive_order":1,"model":"OmniVec2","metrics":{"Mean IoU":"63.6"},"uses_additional_data":true,"paper_date":"2024-01-01","paper":"/paper/omnivec2-a-novel-transformer-based-network","paper_url":"http://openaccess.thecvf.com//content/CVPR2024/html/Srivastava_OmniVec2_-_A_Novel_Transformer_based_Network_for_Large_Scale_CVPR_2024_paper.html","paper_title":"OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":2,"model":"DiffusionMMS (DAT++-S)","metrics":{"Mean IoU":"61.5"},"uses_additional_data":false,"paper_date":"2024-09-23","paper":"/paper/diffusion-based-rgb-d-semantic-segmentation","paper_url":"https://arxiv.org/abs/2409.15117v2","paper_title":"Diffusion-based RGB-D Semantic Segmentation with Deformable Attention Transformer","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":3,"model":"DepthMatch (DINOv2-S)","metrics":{"Mean IoU":"61.4"},"uses_additional_data":true,"paper_date":"2025-05-26","paper":"/paper/depthmatch-semi-supervised-rgb-d-scene","paper_url":"https://arxiv.org/abs/2505.20041v1","paper_title":"DepthMatch: Semi-Supervised RGB-D Scene Parsing through Depth-Guided Regularization","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":4,"model":"GeminiFusion (Swin-Large)","metrics":{"Mean IoU":"60.9"},"uses_additional_data":true,"paper_date":"2024-06-03","paper":"/paper/geminifusion-efficient-pixel-wise-multimodal","paper_url":"https://arxiv.org/abs/2406.01210v2","paper_title":"GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer","code":"https://github.com/jiadingcn/geminifusion","n_code_links":1,"official":{"repos":["jiadingcn/geminifusion"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]},"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":3,"n_samples":10,"n_pointer_only_licence":0,"sample_list":"/paper/geminifusion-efficient-pixel-wise-multimodal#ran","syntology_url":"https://syntology.ai/paper/2406.01210","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.01210"}}}},{"rank_in_archive_order":5,"model":"OmniVec","metrics":{"Mean IoU":"60.8"},"uses_additional_data":true,"paper_date":"2023-11-07","paper":"/paper/omnivec-learning-robust-representations-with","paper_url":"https://arxiv.org/abs/2311.05709v1","paper_title":"OmniVec: Learning robust representations with cross modal sharing","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":6,"model":"GeminiFusion (Swin-Large)","metrics":{"Mean IoU":"60.2"},"uses_additional_data":false,"paper_date":"2024-06-03","paper":"/paper/geminifusion-efficient-pixel-wise-multimodal","paper_url":"https://arxiv.org/abs/2406.01210v2","paper_title":"GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer","code":"https://github.com/jiadingcn/geminifusion","n_code_links":1,"official":{"repos":["jiadingcn/geminifusion"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]},"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":3,"n_samples":10,"n_pointer_only_licence":0,"sample_list":"/paper/geminifusion-efficient-pixel-wise-multimodal#ran","syntology_url":"https://syntology.ai/paper/2406.01210","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.01210"}}}},{"rank_in_archive_order":7,"model":"DPLNet","metrics":{"Mean IoU":"59.3"},"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,"official":null,"syntology":null},{"rank_in_archive_order":8,"model":"HDBFormer","metrics":{"Mean IoU":"59.3%"},"uses_additional_data":false,"paper_date":"2025-04-18","paper":"/paper/hdbformer-efficient-rgb-d-semantic","paper_url":"https://arxiv.org/abs/2504.13579v1","paper_title":"HDBFormer: Efficient RGB-D Semantic Segmentation with A Heterogeneous Dual-Branch Framework","code":"https://github.com/weishuobin/hdbformer","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":9,"model":"EMSANet (2x ResNet-34 NBt1D, PanopticNDT version, finetuned)","metrics":{"Mean IoU":"59.02"},"uses_additional_data":false,"paper_date":"2023-09-24","paper":"/paper/panopticndt-efficient-and-robust-panoptic","paper_url":"https://arxiv.org/abs/2309.13635v2","paper_title":"PanopticNDT: Efficient and Robust Panoptic Mapping","code":"https://github.com/tui-nicr/emsanet","n_code_links":4,"official":{"repos":["tui-nicr/panoptic-mapping"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":7,"n_samples":12,"n_pointer_only_licence":0,"sample_list":"/paper/panopticndt-efficient-and-robust-panoptic#ran","syntology_url":"https://syntology.ai/paper/2309.13635","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.13635"}}}},{"rank_in_archive_order":10,"model":"DFormerv2-L","metrics":{"Mean IoU":"58.4%"},"uses_additional_data":false,"paper_date":"2025-04-07","paper":"/paper/dformerv2-geometry-self-attention-for-rgbd","paper_url":"https://arxiv.org/abs/2504.04701v1","paper_title":"DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation","code":"https://github.com/VCIP-RGBD/DFormer","n_code_links":1,"official":{"repos":["VCIP-RGBD/DFormer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/dformerv2-geometry-self-attention-for-rgbd#ran","syntology_url":"https://syntology.ai/paper/2504.04701","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.04701"}}}},{"rank_in_archive_order":11,"model":"SwinMTL","metrics":{"Mean IoU":"58.14%"},"uses_additional_data":false,"paper_date":"2024-03-15","paper":"/paper/swinmtl-a-shared-architecture-for","paper_url":"https://arxiv.org/abs/2403.10662v1","paper_title":"SwinMTL: A Shared Architecture for Simultaneous Depth Estimation and Semantic Segmentation from Monocular Camera Images","code":"https://github.com/pardistaghavi/swinmtl","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":12,"model":"PolyMaX(ConvNeXt-L)","metrics":{"Mean IoU":"58.08%"},"uses_additional_data":false,"paper_date":"2023-11-09","paper":"/paper/polymax-general-dense-prediction-with-mask","paper_url":"https://arxiv.org/abs/2311.05770v1","paper_title":"PolyMaX: General Dense Prediction with Mask Transformer","code":"https://github.com/google-research/deeplab2","n_code_links":1,"official":{"repos":["google-research/deeplab2"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/polymax-general-dense-prediction-with-mask#ran","syntology_url":"https://syntology.ai/paper/2311.05770","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.05770"}}}},{"rank_in_archive_order":13,"model":"HSPFormer(PVT v2-B4)","metrics":{"Mean IoU":"57.8%"},"uses_additional_data":false,"paper_date":"2025-01-16","paper":"/paper/hspformer-hierarchical-spatial-perception","paper_url":"https://doi.org/10.1109/TITS.2025.3525542","paper_title":"HSPFormer: Hierarchical Spatial Perception Transformer for Semantic Segmentation","code":"https://github.com/SY-Ch/HSPFormer","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":14,"model":"GeminiFusion (MiT-B5)","metrics":{"Mean IoU":"57.7"},"uses_additional_data":false,"paper_date":"2024-06-03","paper":"/paper/geminifusion-efficient-pixel-wise-multimodal","paper_url":"https://arxiv.org/abs/2406.01210v2","paper_title":"GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer","code":"https://github.com/jiadingcn/geminifusion","n_code_links":1,"official":{"repos":["jiadingcn/geminifusion"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]},"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":3,"n_samples":10,"n_pointer_only_licence":0,"sample_list":"/paper/geminifusion-efficient-pixel-wise-multimodal#ran","syntology_url":"https://syntology.ai/paper/2406.01210","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.01210"}}}},{"rank_in_archive_order":15,"model":"DFormerv2-B","metrics":{"Mean IoU":"57.7%"},"uses_additional_data":false,"paper_date":"2025-04-07","paper":"/paper/dformerv2-geometry-self-attention-for-rgbd","paper_url":"https://arxiv.org/abs/2504.04701v1","paper_title":"DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation","code":"https://github.com/VCIP-RGBD/DFormer","n_code_links":1,"official":{"repos":["VCIP-RGBD/DFormer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/dformerv2-geometry-self-attention-for-rgbd#ran","syntology_url":"https://syntology.ai/paper/2504.04701","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.04701"}}}},{"rank_in_archive_order":16,"model":"DFormer-L","metrics":{"Mean IoU":"57.2%"},"uses_additional_data":false,"paper_date":"2023-09-18","paper":"/paper/dformer-rethinking-rgbd-representation","paper_url":"https://arxiv.org/abs/2309.09668v2","paper_title":"DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation","code":"https://github.com/VCIP-RGBD/DFormer","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":17,"model":"CMX (B5)","metrics":{"Mean IoU":"56.9%"},"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,"official":{"repos":["huaaaliu/rgbx_semantic_segmentation"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/cmx-cross-modal-fusion-for-rgb-x-semantic#ran","syntology_url":"https://syntology.ai/paper/2203.04838","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.04838"}}}},{"rank_in_archive_order":18,"model":"CMNeXt (B4)","metrics":{"Mean IoU":"56.9%"},"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,"official":{"repos":["jamycheung/DELIVER"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":0,"n_samples":7,"n_pointer_only_licence":6,"sample_list":"/paper/delivering-arbitrary-modal-semantic#ran","syntology_url":"https://syntology.ai/paper/2303.01480","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.01480"}}}},{"rank_in_archive_order":19,"model":"OMNIVORE (Swin-L, finetuned)","metrics":{"Mean IoU":"56.8%"},"uses_additional_data":false,"paper_date":"2022-01-20","paper":"/paper/omnivore-a-single-model-for-many-visual","paper_url":"https://arxiv.org/abs/2201.08377v2","paper_title":"Omnivore: A Single Model for Many Visual Modalities","code":"https://github.com/towhee-io/towhee","n_code_links":2,"official":{"repos":["facebookresearch/omnivore"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":1,"sample_list":"/paper/omnivore-a-single-model-for-many-visual#ran","syntology_url":"https://syntology.ai/paper/2201.08377","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.08377"}}}},{"rank_in_archive_order":20,"model":"GeminiFusion (MiT-B3)","metrics":{"Mean IoU":"56.8"},"uses_additional_data":false,"paper_date":"2024-06-03","paper":"/paper/geminifusion-efficient-pixel-wise-multimodal","paper_url":"https://arxiv.org/abs/2406.01210v2","paper_title":"GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer","code":"https://github.com/jiadingcn/geminifusion","n_code_links":1,"official":{"repos":["jiadingcn/geminifusion"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]},"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":3,"n_samples":10,"n_pointer_only_licence":0,"sample_list":"/paper/geminifusion-efficient-pixel-wise-multimodal#ran","syntology_url":"https://syntology.ai/paper/2406.01210","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.01210"}}}},{"rank_in_archive_order":21,"model":"CMX (B4)","metrics":{"Mean IoU":"56.3%"},"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,"official":{"repos":["huaaaliu/rgbx_semantic_segmentation"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/cmx-cross-modal-fusion-for-rgb-x-semantic#ran","syntology_url":"https://syntology.ai/paper/2203.04838","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.04838"}}}},{"rank_in_archive_order":22,"model":"MultiMAE (ViT-B)","metrics":{"Mean IoU":"56.0%"},"uses_additional_data":false,"paper_date":"2022-04-04","paper":"/paper/multimae-multi-modal-multi-task-masked","paper_url":"https://arxiv.org/abs/2204.01678v1","paper_title":"MultiMAE: Multi-modal Multi-task Masked Autoencoders","code":"https://github.com/EPFL-VILAB/MultiMAE","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":23,"model":"DFormerv2-S","metrics":{"Mean IoU":"56.0%"},"uses_additional_data":false,"paper_date":"2025-04-07","paper":"/paper/dformerv2-geometry-self-attention-for-rgbd","paper_url":"https://arxiv.org/abs/2504.04701v1","paper_title":"DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation","code":"https://github.com/VCIP-RGBD/DFormer","n_code_links":1,"official":{"repos":["VCIP-RGBD/DFormer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/dformerv2-geometry-self-attention-for-rgbd#ran","syntology_url":"https://syntology.ai/paper/2504.04701","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.04701"}}}},{"rank_in_archive_order":24,"model":"SMMCL (SegNeXt-B)","metrics":{"Mean IoU":"55.8%"},"uses_additional_data":false,"paper_date":"2023-08-23","paper":"/paper/understanding-dark-scenes-by-contrasting","paper_url":"https://arxiv.org/abs/2308.12320v2","paper_title":"Understanding Dark Scenes by Contrasting Multi-Modal Observations","code":"https://github.com/palmdong/smmcl","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":25,"model":"DFormer-B","metrics":{"Mean IoU":"55.6%"},"uses_additional_data":false,"paper_date":"2023-09-18","paper":"/paper/dformer-rethinking-rgbd-representation","paper_url":"https://arxiv.org/abs/2309.09668v2","paper_title":"DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation","code":"https://github.com/VCIP-RGBD/DFormer","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":26,"model":"ComPtr (Swin-B)","metrics":{"Mean IoU":"55.5%"},"uses_additional_data":false,"paper_date":"2023-07-23","paper":"/paper/comptr-towards-diverse-bi-source-dense","paper_url":"https://arxiv.org/abs/2307.12349v1","paper_title":"ComPtr: Towards Diverse Bi-source Dense Prediction Tasks via A Simple yet General Complementary Transformer","code":"https://github.com/lartpang/comptr","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":27,"model":"AsymFormer","metrics":{"Mean IoU":"55.3%"},"uses_additional_data":false,"paper_date":"2023-09-25","paper":"/paper/asymformer-asymmetrical-cross-modal","paper_url":"https://arxiv.org/abs/2309.14065v7","paper_title":"AsymFormer: Asymmetrical Cross-Modal Representation Learning for Mobile Platform Real-Time RGB-D Semantic Segmentation","code":"https://github.com/Fourier7754/AsymFormer","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":28,"model":"OMNIVORE (Swin-B, finetuned)","metrics":{"Mean IoU":"55.1%"},"uses_additional_data":false,"paper_date":"2022-01-20","paper":"/paper/omnivore-a-single-model-for-many-visual","paper_url":"https://arxiv.org/abs/2201.08377v2","paper_title":"Omnivore: A Single Model for Many Visual Modalities","code":"https://github.com/towhee-io/towhee","n_code_links":2,"official":{"repos":["facebookresearch/omnivore"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":1,"sample_list":"/paper/omnivore-a-single-model-for-many-visual#ran","syntology_url":"https://syntology.ai/paper/2201.08377","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.08377"}}}},{"rank_in_archive_order":29,"model":"HAPNet","metrics":{"Mean Accuracy":"68.8","Mean IoU":"55.0"},"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,"official":null,"syntology":null},{"rank_in_archive_order":30,"model":"CMX (B2)","metrics":{"Mean IoU":"54.4%"},"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,"official":{"repos":["huaaaliu/rgbx_semantic_segmentation"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/cmx-cross-modal-fusion-for-rgb-x-semantic#ran","syntology_url":"https://syntology.ai/paper/2203.04838","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.04838"}}}},{"rank_in_archive_order":31,"model":"TokenFusion (S)","metrics":{"Mean IoU":"54.2%"},"uses_additional_data":false,"paper_date":"2022-04-19","paper":"/paper/multimodal-token-fusion-for-vision","paper_url":"https://arxiv.org/abs/2204.08721v2","paper_title":"Multimodal Token Fusion for Vision Transformers","code":"https://github.com/huawei-noah/noah-research/tree/master/TokenFusion","n_code_links":11,"official":{"repos":["yikaiw/TokenFusion","huawei-noah/noah-research","mindspore-ai/models"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":1,"sample_list":"/paper/multimodal-token-fusion-for-vision#ran","syntology_url":"https://syntology.ai/paper/2204.08721","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.08721"}}}},{"rank_in_archive_order":32,"model":"SMMCL (SegFormer-B2)","metrics":{"Mean IoU":"53.7%"},"uses_additional_data":false,"paper_date":"2023-08-23","paper":"/paper/understanding-dark-scenes-by-contrasting","paper_url":"https://arxiv.org/abs/2308.12320v2","paper_title":"Understanding Dark Scenes by Contrasting Multi-Modal Observations","code":"https://github.com/palmdong/smmcl","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":33,"model":"DFormer-S","metrics":{"Mean IoU":"53.6%"},"uses_additional_data":false,"paper_date":"2023-09-18","paper":"/paper/dformer-rethinking-rgbd-representation","paper_url":"https://arxiv.org/abs/2309.09668v2","paper_title":"DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation","code":"https://github.com/VCIP-RGBD/DFormer","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":34,"model":"InvPT","metrics":{"Mean IoU":"53.56%"},"uses_additional_data":false,"paper_date":"2022-03-15","paper":"/paper/inverted-pyramid-multi-task-transformer-for","paper_url":"https://arxiv.org/abs/2203.07997v3","paper_title":"InvPT: Inverted Pyramid Multi-task Transformer for Dense Scene Understanding","code":"https://github.com/prismformore/InvPT","n_code_links":1,"official":{"repos":["prismformore/InvPT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":1,"sample_list":"/paper/inverted-pyramid-multi-task-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2203.07997","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.07997"}}}},{"rank_in_archive_order":35,"model":"HS3-Fuse (ResNet-101)","metrics":{"Mean IoU":"53.5%"},"uses_additional_data":false,"paper_date":"2021-11-03","paper":"/paper/hs3-learning-with-proper-task-complexity-in","paper_url":"https://arxiv.org/abs/2111.02333v1","paper_title":"HS3: Learning with Proper Task Complexity in Hierarchically Supervised Semantic Segmentation","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":36,"model":"PDCNet (ResNet-101)","metrics":{"Mean IoU":"53.5%"},"uses_additional_data":false,"paper_date":"2023-02-23","paper":"/paper/pixel-difference-convolutional-network-for","paper_url":"https://arxiv.org/abs/2302.11951v1","paper_title":"Pixel Difference Convolutional Network for RGB-D Semantic Segmentation","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":37,"model":"EMSANet (2x ResNet-34 NBt1D, finetuned)","metrics":{"Mean IoU":"53.34%"},"uses_additional_data":true,"paper_date":"2022-07-10","paper":"/paper/efficient-multi-task-rgb-d-scene-analysis-for","paper_url":"https://arxiv.org/abs/2207.04526v1","paper_title":"Efficient Multi-Task RGB-D Scene Analysis for Indoor Environments","code":"https://github.com/tui-nicr/emsanet","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":38,"model":"DCANet (ResNet-101)","metrics":{"Mean IoU":"53.3%"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/dcanet-differential-convolution-attention","paper_url":"https://arxiv.org/abs/2210.06747v1","paper_title":"DCANet: Differential Convolution Attention Network for RGB-D Semantic Segmentation","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":39,"model":"TokenFusion (Ti)","metrics":{"Mean IoU":"53.3%"},"uses_additional_data":false,"paper_date":"2022-04-19","paper":"/paper/multimodal-token-fusion-for-vision","paper_url":"https://arxiv.org/abs/2204.08721v2","paper_title":"Multimodal Token Fusion for Vision Transformers","code":"https://github.com/huawei-noah/noah-research/tree/master/TokenFusion","n_code_links":11,"official":{"repos":["yikaiw/TokenFusion","huawei-noah/noah-research","mindspore-ai/models"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":1,"sample_list":"/paper/multimodal-token-fusion-for-vision#ran","syntology_url":"https://syntology.ai/paper/2204.08721","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.08721"}}}},{"rank_in_archive_order":40,"model":"InverseForm (ResNet-101)","metrics":{"Mean IoU":"53.1%"},"uses_additional_data":false,"paper_date":"2021-04-06","paper":"/paper/inverseform-a-loss-function-for-structured","paper_url":"https://arxiv.org/abs/2104.02745v2","paper_title":"InverseForm: A Loss Function for Structured Boundary-Aware Segmentation","code":"https://github.com/Qualcomm-AI-research/InverseForm","n_code_links":1,"official":null,"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":3,"sample_list":"/paper/inverseform-a-loss-function-for-structured#ran","syntology_url":"https://syntology.ai/paper/2104.02745","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.02745"}}}},{"rank_in_archive_order":41,"model":"CAINet (MobileNet-V2)","metrics":{"Mean IoU":"52.6%"},"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,"official":null,"syntology":null},{"rank_in_archive_order":42,"model":"CEN-PSPNet (ResNet-152)","metrics":{"Mean IoU":"52.5%"},"uses_additional_data":false,"paper_date":"2021-12-04","paper":"/paper/channel-exchanging-networks-for-multimodal","paper_url":"https://arxiv.org/abs/2112.02252v2","paper_title":"Channel Exchanging Networks for Multimodal and Multitask Dense Image Prediction","code":"https://github.com/yikaiw/CEN","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":43,"model":"AMF (ResNet-50)","metrics":{"Mean IoU":"52.5%"},"uses_additional_data":false,"paper_date":"2022-01-05","paper":"/paper/attention-based-dual-supervised-decoder-for","paper_url":"https://arxiv.org/abs/2201.01427v2","paper_title":"Attention-based Dual Supervised Decoder for RGBD Semantic Segmentation","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":44,"model":"SMMCL (ResNet-101)","metrics":{"Mean IoU":"52.5%"},"uses_additional_data":false,"paper_date":"2023-08-23","paper":"/paper/understanding-dark-scenes-by-contrasting","paper_url":"https://arxiv.org/abs/2308.12320v2","paper_title":"Understanding Dark Scenes by Contrasting Multi-Modal Observations","code":"https://github.com/palmdong/smmcl","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":45,"model":"SA-Gate","metrics":{"Mean IoU":"52.4%"},"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,"official":null,"syntology":null},{"rank_in_archive_order":46,"model":"Warp-Refine","metrics":{"Mean IoU":"52.2%"},"uses_additional_data":false,"paper_date":"2021-09-28","paper":"/paper/warp-refine-propagation-semi-supervised-auto","paper_url":"https://arxiv.org/abs/2109.13432v1","paper_title":"Warp-Refine Propagation: Semi-Supervised Auto-labeling via Cycle-consistency","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":47,"model":"FSFNet","metrics":{"Mean IoU":"52.0%"},"uses_additional_data":false,"paper_date":"2021-05-10","paper":"/paper/deep-feature-selection-and-fusion-for-rgb-d","paper_url":"https://arxiv.org/abs/2105.04102v1","paper_title":"Deep feature selection-and-fusion for RGB-D semantic segmentation","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":48,"model":"VCD+ACNet (ResNet-50)","metrics":{"Mean IoU":"51.9%"},"uses_additional_data":false,"paper_date":"2020-06-01","paper":"/paper/variational-context-deformable-convnets-for","paper_url":"http://openaccess.thecvf.com/content_CVPR_2020/html/Xiong_Variational_Context-Deformable_ConvNets_for_Indoor_Scene_Parsing_CVPR_2020_paper.html","paper_title":"Variational Context-Deformable ConvNets for Indoor Scene Parsing","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":49,"model":"MIPANet (ResNet50)","metrics":{"Mean IoU":"51.9%"},"uses_additional_data":false,"paper_date":"2023-11-19","paper":"/paper/optimizing-rgb-d-semantic-segmentation","paper_url":"https://arxiv.org/abs/2311.11312v2","paper_title":"Optimizing rgb-d semantic segmentation through multi-modal interaction and pooling attention","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":50,"model":"DFormer-T","metrics":{"Mean IoU":"51.8%"},"uses_additional_data":false,"paper_date":"2023-09-18","paper":"/paper/dformer-rethinking-rgbd-representation","paper_url":"https://arxiv.org/abs/2309.09668v2","paper_title":"DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation","code":"https://github.com/VCIP-RGBD/DFormer","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":51,"model":"ShapeConv (ResNext-101)","metrics":{"Mean IoU":"51.3%"},"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,"official":{"repos":["hanchaoleng/shapeconv"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":0,"sample_list":"/paper/shapeconv-shape-aware-convolutional-layer-for#ran","syntology_url":"https://syntology.ai/paper/2108.10528","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.10528"}}}},{"rank_in_archive_order":52,"model":"EMSAFormer (SwinV2-T-128-Multi-Aug)","metrics":{"Mean IoU":"51.26%"},"uses_additional_data":false,"paper_date":"2023-06-08","paper":"/paper/efficient-multi-task-scene-analysis-with-rgb","paper_url":"https://arxiv.org/abs/2306.05242v1","paper_title":"Efficient Multi-Task Scene Analysis with RGB-D Transformers","code":"https://github.com/tui-nicr/nicr-scene-analysis-datasets","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":53,"model":"Z-ACN (ResNet-101)","metrics":{"Mean IoU":"51.24%"},"uses_additional_data":false,"paper_date":"2022-06-08","paper":"/paper/depth-adapted-cnns-for-rgb-d-semantic","paper_url":"https://arxiv.org/abs/2206.03939v1","paper_title":"Depth-Adapted CNNs for RGB-D Semantic Segmentation","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":54,"model":"AsymFusion (ResNet-152)","metrics":{"Mean IoU":"51.2%"},"uses_additional_data":false,"paper_date":"2021-08-11","paper":"/paper/learning-deep-multimodal-feature","paper_url":"https://arxiv.org/abs/2108.05009v1","paper_title":"Learning Deep Multimodal Feature Representation with Asymmetric Multi-layer Fusion","code":"https://github.com/yikaiw/AsymFusion","n_code_links":1,"official":{"repos":["yikaiw/AsymFusion"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official"]},"syntology":{"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":5,"n_samples":11,"n_pointer_only_licence":0,"sample_list":"/paper/learning-deep-multimodal-feature#ran","syntology_url":"https://syntology.ai/paper/2108.05009","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.05009"}}}},{"rank_in_archive_order":55,"model":"DynMM (ResNet-50)","metrics":{"Mean IoU":"51.0%"},"uses_additional_data":false,"paper_date":"2022-03-31","paper":"/paper/dynamic-multimodal-fusion","paper_url":"https://arxiv.org/abs/2204.00102v2","paper_title":"Dynamic Multimodal Fusion","code":"https://github.com/zihuixue/dynmm","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":56,"model":"SGNet (ResNet-101)","metrics":{"Mean IoU":"51.0%"},"uses_additional_data":false,"paper_date":"2020-04-09","paper":"/paper/spatial-information-guided-convolution-for","paper_url":"https://arxiv.org/abs/2004.04534v2","paper_title":"Spatial Information Guided Convolution for Real-Time RGBD Semantic Segmentation","code":"https://github.com/LinZhuoChen/SGNet","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":57,"model":"PSD-ResNet50","metrics":{"Mean IoU":"51.0%"},"uses_additional_data":false,"paper_date":"2020-06-01","paper":"/paper/pattern-structure-diffusion-for-multi-task","paper_url":"http://openaccess.thecvf.com/content_CVPR_2020/html/Zhou_Pattern-Structure_Diffusion_for_Multi-Task_Learning_CVPR_2020_paper.html","paper_title":"Pattern-Structure Diffusion for Multi-Task Learning","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":58,"model":"Malleable 2.5D (ResNet-101)","metrics":{"Mean IoU":"50.9%"},"uses_additional_data":false,"paper_date":"2020-07-18","paper":"/paper/malleable-2-5d-convolution-learning-receptive","paper_url":"https://arxiv.org/abs/2007.09365v1","paper_title":"Malleable 2.5D Convolution: Learning Receptive Fields along the Depth-axis for RGB-D Scene Parsing","code":"https://github.com/charlesCXK/RGBD_Semantic_Segmentation_PyTorch","n_code_links":2,"official":{"repos":["charlesCXK/RGBD_Semantic_Segmentation_PyTorch"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":5,"n_samples":14,"n_pointer_only_licence":3,"sample_list":"/paper/malleable-2-5d-convolution-learning-receptive#ran","syntology_url":"https://syntology.ai/paper/2007.09365","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.09365"}}}},{"rank_in_archive_order":59,"model":"ICM","metrics":{"Mean IoU":"50.70"},"uses_additional_data":false,"paper_date":"2019-06-01","paper":"/paper/scene-parsing-via-integrated-classification","paper_url":"http://openaccess.thecvf.com/content_CVPR_2019/html/Shi_Scene_Parsing_via_Integrated_Classification_Model_and_Variance-Based_Regularization_CVPR_2019_paper.html","paper_title":"Scene Parsing via Integrated Classification Model and Variance-Based Regularization","code":"https://github.com/shihengcan/ICM-matcaffe","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":60,"model":"SANet","metrics":{"Mean IoU":"50.7%"},"uses_additional_data":false,"paper_date":"2020-11-04","paper":"/paper/multi-layer-feature-aggregation-for-deep","paper_url":"https://arxiv.org/abs/2011.02572v1","paper_title":"Multi-layer Feature Aggregation for Deep Scene Parsing Models","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":61,"model":"VCD+RedNet (ResNet-50)","metrics":{"Mean IoU":"50.7%"},"uses_additional_data":false,"paper_date":"2020-06-01","paper":"/paper/variational-context-deformable-convnets-for","paper_url":"http://openaccess.thecvf.com/content_CVPR_2020/html/Xiong_Variational_Context-Deformable_ConvNets_for_Indoor_Scene_Parsing_CVPR_2020_paper.html","paper_title":"Variational Context-Deformable ConvNets for Indoor Scene Parsing","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":62,"model":"HaarNet","metrics":{"Mean IoU":"50.7%"},"uses_additional_data":false,"paper_date":"2023-10-11","paper":"/paper/haarnet-large-scale-linear-morphological","paper_url":"https://arxiv.org/abs/2310.07669v1","paper_title":"HaarNet: Large-scale Linear-Morphological Hybrid Network for RGB-D Semantic Segmentation","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":63,"model":"PAP (ResNet-50)","metrics":{"Mean IoU":"50.4%"},"uses_additional_data":false,"paper_date":"2019-06-08","paper":"/paper/pattern-affinitive-propagation-across-depth-1","paper_url":"https://arxiv.org/abs/1906.03525v1","paper_title":"Pattern-Affinitive Propagation across Depth, Surface Normal and Semantic Segmentation","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":64,"model":"Cerberus","metrics":{"Mean IoU":"50.4%"},"uses_additional_data":false,"paper_date":"2021-11-24","paper":"/paper/cerberus-transformer-joint-semantic","paper_url":"https://arxiv.org/abs/2111.12608v2","paper_title":"Cerberus Transformer: Joint Semantic, Affordance and Attribute Parsing","code":"https://github.com/open-air-sun/cerberus","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":65,"model":"ESANet (R34-NBt1D)","metrics":{"Mean IoU":"50.30"},"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,"official":null,"syntology":null},{"rank_in_archive_order":66,"model":"Z-ACN (ResNet-50)","metrics":{"Mean IoU":"50.05%"},"uses_additional_data":false,"paper_date":"2022-06-08","paper":"/paper/depth-adapted-cnns-for-rgb-d-semantic","paper_url":"https://arxiv.org/abs/2206.03939v1","paper_title":"Depth-Adapted CNNs for RGB-D Semantic Segmentation","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":67,"model":"Malleable 2.5D (ResNet-50)","metrics":{"Mean IoU":"49.7%"},"uses_additional_data":false,"paper_date":"2020-07-18","paper":"/paper/malleable-2-5d-convolution-learning-receptive","paper_url":"https://arxiv.org/abs/2007.09365v1","paper_title":"Malleable 2.5D Convolution: Learning Receptive Fields along the Depth-axis for RGB-D Scene Parsing","code":"https://github.com/charlesCXK/RGBD_Semantic_Segmentation_PyTorch","n_code_links":2,"official":{"repos":["charlesCXK/RGBD_Semantic_Segmentation_PyTorch"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":5,"n_samples":14,"n_pointer_only_licence":3,"sample_list":"/paper/malleable-2-5d-convolution-learning-receptive#ran","syntology_url":"https://syntology.ai/paper/2007.09365","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.09365"}}}},{"rank_in_archive_order":68,"model":"MMANet","metrics":{"Mean IoU":"49.62%"},"uses_additional_data":false,"paper_date":"2023-04-17","paper":"/paper/mmanet-margin-aware-distillation-and-modality","paper_url":"https://arxiv.org/abs/2304.08028v1","paper_title":"MMANet: Margin-aware Distillation and Modality-aware Regularization for Incomplete Multimodal Learning","code":"https://github.com/shicaiwei123/mmanet","n_code_links":1,"official":{"repos":["shicaiwei123/mmanet"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":7,"ran_from_kinds":["official"]},"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":7,"n_samples":14,"n_pointer_only_licence":0,"sample_list":"/paper/mmanet-margin-aware-distillation-and-modality#ran","syntology_url":"https://syntology.ai/paper/2304.08028","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.08028"}}}},{"rank_in_archive_order":69,"model":"SGACNet (R34-NBt1D)","metrics":{"Mean IoU":"49.4%"},"uses_additional_data":false,"paper_date":"2023-08-11","paper":"/paper/spatial-information-guided-adaptive-context","paper_url":"https://arxiv.org/abs/2308.06024v1","paper_title":"Spatial-information Guided Adaptive Context-aware Network for Efficient RGB-D Semantic Segmentation","code":"https://github.com/mvme-hbut/sgacnet","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":70,"model":"ComPtr (Swin-T)","metrics":{"Mean IoU":"49.2%"},"uses_additional_data":false,"paper_date":"2023-07-23","paper":"/paper/comptr-towards-diverse-bi-source-dense","paper_url":"https://arxiv.org/abs/2307.12349v1","paper_title":"ComPtr: Towards Diverse Bi-source Dense Prediction Tasks via A Simple yet General Complementary Transformer","code":"https://github.com/lartpang/comptr","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":71,"model":"Z-ACN (ResNet-34)","metrics":{"Mean IoU":"49.15%"},"uses_additional_data":false,"paper_date":"2022-06-08","paper":"/paper/depth-adapted-cnns-for-rgb-d-semantic","paper_url":"https://arxiv.org/abs/2206.03939v1","paper_title":"Depth-Adapted CNNs for RGB-D Semantic Segmentation","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":72,"model":"UMT","metrics":{"Mean IoU":"49.14%"},"uses_additional_data":false,"paper_date":"2021-06-21","paper":"/paper/improving-multi-modal-learning-with-uni-modal","paper_url":"https://arxiv.org/abs/2106.11059v1","paper_title":"Improving Multi-Modal Learning with Uni-Modal Teachers","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":73,"model":"MTI-Net (HRNet-48)","metrics":{"Mean IoU":"49.0"},"uses_additional_data":false,"paper_date":"2020-01-19","paper":"/paper/mti-net-multi-scale-task-interaction-networks","paper_url":"https://arxiv.org/abs/2001.06902v5","paper_title":"MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learning","code":"https://github.com/SimonVandenhende/Multi-Task-Learning-PyTorch","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":74,"model":"ShapeConv (ResNet-101)","metrics":{"Mean IoU":"49.0%"},"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,"official":{"repos":["hanchaoleng/shapeconv"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":0,"sample_list":"/paper/shapeconv-shape-aware-convolutional-layer-for#ran","syntology_url":"https://syntology.ai/paper/2108.10528","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.10528"}}}},{"rank_in_archive_order":75,"model":"MKE","metrics":{"Mean IoU":"48.88%"},"uses_additional_data":false,"paper_date":"2021-03-26","paper":"/paper/multimodal-knowledge-expansion","paper_url":"https://arxiv.org/abs/2103.14431v3","paper_title":"Multimodal Knowledge Expansion","code":"https://github.com/zihuixue/mke","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":76,"model":"ShapeConv (ResNet-50)","metrics":{"Mean IoU":"48.8%"},"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,"official":{"repos":["hanchaoleng/shapeconv"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":0,"sample_list":"/paper/shapeconv-shape-aware-convolutional-layer-for#ran","syntology_url":"https://syntology.ai/paper/2108.10528","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.10528"}}}},{"rank_in_archive_order":77,"model":"mmFormer","metrics":{"Mean IoU":"48.45%"},"uses_additional_data":false,"paper_date":"2022-06-06","paper":"/paper/mmformer-multimodal-medical-transformer-for","paper_url":"https://arxiv.org/abs/2206.02425v2","paper_title":"mmFormer: Multimodal Medical Transformer for Incomplete Multimodal Learning of Brain Tumor Segmentation","code":"https://github.com/yaozhang93/mmformer","n_code_links":1,"official":{"repos":["yaozhang93/mmformer"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":4,"ran_from_kinds":["official"]},"syntology":{"n_ran":13,"n_constructed":0,"n_ran_checked":10,"n_instrument":3,"n_unverified":4,"n_samples":17,"n_pointer_only_licence":1,"sample_list":"/paper/mmformer-multimodal-medical-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2206.02425","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.02425"}}}},{"rank_in_archive_order":78,"model":"ACNet","metrics":{"Mean IoU":"48.3%"},"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,"official":null,"syntology":null},{"rank_in_archive_order":79,"model":"SGACNet (R18-NBt1D)","metrics":{"Mean IoU":"48.2%"},"uses_additional_data":false,"paper_date":"2023-08-11","paper":"/paper/spatial-information-guided-adaptive-context","paper_url":"https://arxiv.org/abs/2308.06024v1","paper_title":"Spatial-information Guided Adaptive Context-aware Network for Efficient RGB-D Semantic Segmentation","code":"https://github.com/mvme-hbut/sgacnet","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":80,"model":"ESANet (R18-NBt1D )","metrics":{"Mean IoU":"48.17"},"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,"official":null,"syntology":null},{"rank_in_archive_order":81,"model":"RFNet","metrics":{"Mean IoU":"48.13%"},"uses_additional_data":false,"paper_date":"2021-01-01","paper":"/paper/rfnet-region-aware-fusion-network-for","paper_url":"http://openaccess.thecvf.com//content/ICCV2021/html/Ding_RFNet_Region-Aware_Fusion_Network_for_Incomplete_Multi-Modal_Brain_Tumor_Segmentation_ICCV_2021_paper.html","paper_title":"RFNet: Region-Aware Fusion Network for Incomplete Multi-Modal Brain Tumor Segmentation","code":"https://github.com/dyh127/RFNet","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":82,"model":"TupleInfoNCE","metrics":{"Mean IoU":"48.1%"},"uses_additional_data":false,"paper_date":"2021-07-06","paper":"/paper/contrastive-multimodal-fusion-with","paper_url":"https://arxiv.org/abs/2107.02575v1","paper_title":"Contrastive Multimodal Fusion with TupleInfoNCE","code":"https://github.com/hoi4d/TupleInfoNCE","n_code_links":1,"official":{"repos":["hoi4d/TupleInfoNCE"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":4,"n_samples":7,"n_pointer_only_licence":0,"sample_list":"/paper/contrastive-multimodal-fusion-with#ran","syntology_url":"https://syntology.ai/paper/2107.02575","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.02575"}}}},{"rank_in_archive_order":83,"model":"DDSC (ResNet-101)","metrics":{"Mean IoU":"48.1%"},"uses_additional_data":false,"paper_date":"2018-06-01","paper":"/paper/dense-decoder-shortcut-connections-for-single","paper_url":"http://openaccess.thecvf.com/content_cvpr_2018/html/Bilinski_Dense_Decoder_Shortcut_CVPR_2018_paper.html","paper_title":"Dense Decoder Shortcut Connections for Single-Pass Semantic Segmentation","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":84,"model":"CFN","metrics":{"Mean IoU":"47.7%"},"uses_additional_data":false,"paper_date":"2017-10-01","paper":"/paper/cascaded-feature-network-for-semantic","paper_url":"http://openaccess.thecvf.com/content_iccv_2017/html/Lin_Cascaded_Feature_Network_ICCV_2017_paper.html","paper_title":"Cascaded Feature Network for Semantic Segmentation of RGB-D Images","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":85,"model":"FDNet (DenseNet264)","metrics":{"Mean IoU":"47.4%"},"uses_additional_data":false,"paper_date":"2019-05-22","paper":"/paper/learning-fully-dense-neural-networks-for","paper_url":"https://arxiv.org/abs/1905.08929v1","paper_title":"Learning Fully Dense Neural Networks for Image Semantic Segmentation","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":86,"model":"RedNet","metrics":{"Mean IoU":"47.2%"},"uses_additional_data":false,"paper_date":"2018-06-04","paper":"/paper/rednet-residual-encoder-decoder-network-for","paper_url":"http://arxiv.org/abs/1806.01054v2","paper_title":"RedNet: Residual Encoder-Decoder Network for indoor RGB-D Semantic Segmentation","code":"https://github.com/JindongJiang/RedNet","n_code_links":8,"official":{"repos":["JindongJiang/RedNet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_samples":9,"n_pointer_only_licence":0,"sample_list":"/paper/rednet-residual-encoder-decoder-network-for#ran","syntology_url":"https://syntology.ai/paper/1806.01054","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.01054"}}}},{"rank_in_archive_order":87,"model":"Z-ACN (ResNet-18)","metrics":{"Mean IoU":"47.02%"},"uses_additional_data":false,"paper_date":"2022-06-08","paper":"/paper/depth-adapted-cnns-for-rgb-d-semantic","paper_url":"https://arxiv.org/abs/2206.03939v1","paper_title":"Depth-Adapted CNNs for RGB-D Semantic Segmentation","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":88,"model":"TRL (ResNet-101)","metrics":{"Mean IoU":"46.8%"},"uses_additional_data":false,"paper_date":"2018-09-01","paper":"/paper/joint-task-recursive-learning-for-semantic","paper_url":"http://openaccess.thecvf.com/content_ECCV_2018/html/Zhenyu_Zhang_Joint_Task-Recursive_Learning_ECCV_2018_paper.html","paper_title":"Joint Task-Recursive Learning for Semantic Segmentation and Depth Estimation","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":89,"model":"RefineNet (ResNet-101)","metrics":{"Mean IoU":"46.5%"},"uses_additional_data":false,"paper_date":"2016-11-20","paper":"/paper/refinenet-multi-path-refinement-networks-for","paper_url":"http://arxiv.org/abs/1611.06612v3","paper_title":"RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation","code":"https://github.com/guosheng/refinenet","n_code_links":13,"official":{"repos":["guosheng/refinenet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":1,"sample_list":"/paper/refinenet-multi-path-refinement-networks-for#ran","syntology_url":"https://syntology.ai/paper/1611.06612","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.06612"}}}},{"rank_in_archive_order":90,"model":"PGT (Swin-S)","metrics":{"Mean IoU":"46.43"},"uses_additional_data":false,"paper_date":"2023-07-28","paper":"/paper/prompt-guided-transformer-for-multi-task","paper_url":"https://arxiv.org/abs/2307.15362v1","paper_title":"Prompt Guided Transformer for Multi-Task Dense Prediction","code":"https://github.com/innovator-zero/MTDP_Lib","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":91,"model":"ATRC","metrics":{"Mean IoU":"46.33%"},"uses_additional_data":false,"paper_date":"2021-04-28","paper":"/paper/exploring-relational-context-for-multi-task","paper_url":"https://arxiv.org/abs/2104.13874v2","paper_title":"Exploring Relational Context for Multi-Task Dense Prediction","code":"https://github.com/brdav/atrc","n_code_links":1,"official":{"repos":["brdav/atrc"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/exploring-relational-context-for-multi-task#ran","syntology_url":"https://syntology.ai/paper/2104.13874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.13874"}}}},{"rank_in_archive_order":92,"model":"LS-DeconvNet","metrics":{"Mean IoU":"45.9%"},"uses_additional_data":false,"paper_date":"2017-07-01","paper":"/paper/locality-sensitive-deconvolution-networks","paper_url":"http://openaccess.thecvf.com/content_cvpr_2017/html/Cheng_Locality-Sensitive_Deconvolution_Networks_CVPR_2017_paper.html","paper_title":"Locality-Sensitive Deconvolution Networks With Gated Fusion for RGB-D Indoor Semantic Segmentation","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":93,"model":"VCD+DeepLab (VGG16)","metrics":{"Mean IoU":"45.3"},"uses_additional_data":false,"paper_date":"2020-06-01","paper":"/paper/variational-context-deformable-convnets-for","paper_url":"http://openaccess.thecvf.com/content_CVPR_2020/html/Xiong_Variational_Context-Deformable_ConvNets_for_Indoor_Scene_Parsing_CVPR_2020_paper.html","paper_title":"Variational Context-Deformable ConvNets for Indoor Scene Parsing","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":94,"model":"SOSD-Net","metrics":{"Mean IoU":"45.0%"},"uses_additional_data":false,"paper_date":"2021-01-19","paper":"/paper/sosd-net-joint-semantic-object-segmentation","paper_url":"https://arxiv.org/abs/2101.07422v1","paper_title":"SOSD-Net: Joint Semantic Object Segmentation and Depth Estimation from Monocular images","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":95,"model":"MMAF-Net-152","metrics":{"Mean IoU":"44.8%"},"uses_additional_data":false,"paper_date":"2019-12-25","paper":"/paper/multi-modal-attention-based-fusion-model-for","paper_url":"https://arxiv.org/abs/1912.11691v1","paper_title":"Multi-Modal Attention-based Fusion Model for Semantic Segmentation of RGB-Depth Images","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":96,"model":"RecurrentSceneParsing","metrics":{"Mean IoU":"44.5%"},"uses_additional_data":false,"paper_date":"2017-05-20","paper":"/paper/recurrent-scene-parsing-with-perspective","paper_url":"http://arxiv.org/abs/1705.07238v2","paper_title":"Recurrent Scene Parsing with Perspective Understanding in the Loop","code":"https://github.com/aimerykong/Recurrent-Scene-Parsing-with-Perspective-Understanding-in-the-loop","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":97,"model":"Light-Weight-RefineNet-152","metrics":{"Mean IoU":"44.4%"},"uses_additional_data":false,"paper_date":"2018-10-08","paper":"/paper/light-weight-refinenet-for-real-time-semantic","paper_url":"http://arxiv.org/abs/1810.03272v1","paper_title":"Light-Weight RefineNet for Real-Time Semantic Segmentation","code":"https://github.com/DrSleep/light-weight-refinenet","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":98,"model":"Depth-aware CNN","metrics":{"Mean IoU":"43.9%"},"uses_additional_data":false,"paper_date":"2018-03-19","paper":"/paper/depth-aware-cnn-for-rgb-d-segmentation","paper_url":"http://arxiv.org/abs/1803.06791v1","paper_title":"Depth-aware CNN for RGB-D Segmentation","code":"https://github.com/laughtervv/DepthAwareCNN","n_code_links":4,"official":{"repos":["laughtervv/DepthAwareCNN"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":5,"n_samples":11,"n_pointer_only_licence":0,"sample_list":"/paper/depth-aware-cnn-for-rgb-d-segmentation#ran","syntology_url":"https://syntology.ai/paper/1803.06791","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.06791"}}}},{"rank_in_archive_order":99,"model":"Light-Weight-RefineNet-101","metrics":{"Mean IoU":"43.6%"},"uses_additional_data":false,"paper_date":"2018-10-08","paper":"/paper/light-weight-refinenet-for-real-time-semantic","paper_url":"http://arxiv.org/abs/1810.03272v1","paper_title":"Light-Weight RefineNet for Real-Time Semantic Segmentation","code":"https://github.com/DrSleep/light-weight-refinenet","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":100,"model":"TD2-PSP50","metrics":{"Mean IoU":"43.5"},"uses_additional_data":false,"paper_date":"2020-04-03","paper":"/paper/temporally-distributed-networks-for-fast","paper_url":"https://arxiv.org/abs/2004.01800v2","paper_title":"Temporally Distributed Networks for Fast Video Semantic Segmentation","code":"https://github.com/feinanshan/TDNet","n_code_links":1,"official":null,"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":2,"sample_list":"/paper/temporally-distributed-networks-for-fast#ran","syntology_url":"https://syntology.ai/paper/2004.01800","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.01800"}}}},{"rank_in_archive_order":101,"model":"NDDR-CNN","metrics":{"Mean IoU":"43.3%"},"uses_additional_data":false,"paper_date":"2018-01-25","paper":"/paper/nddr-cnn-layer-wise-feature-fusing-in-multi","paper_url":"http://arxiv.org/abs/1801.08297v4","paper_title":"NDDR-CNN: Layerwise Feature Fusing in Multi-Task CNNs by Neural Discriminative Dimensionality Reduction","code":"https://github.com/ethanygao/NDDR-CNN","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":102,"model":"3DGNN","metrics":{"Mean IoU":"43.1%"},"uses_additional_data":false,"paper_date":"2017-10-01","paper":"/paper/3d-graph-neural-networks-for-rgbd-semantic","paper_url":"http://openaccess.thecvf.com/content_iccv_2017/html/Qi_3D_Graph_Neural_ICCV_2017_paper.html","paper_title":"3D Graph Neural Networks for RGBD Semantic Segmentation","code":"https://github.com/yanx27/3DGNN_pytorch","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":103,"model":"CI-Net","metrics":{"Mean IoU":"42.6%"},"uses_additional_data":false,"paper_date":"2021-07-29","paper":"/paper/ci-net-contextual-information-for-joint","paper_url":"https://arxiv.org/abs/2107.13800v2","paper_title":"CI-Net: Contextual Information for Joint Semantic Segmentation and Depth Estimation","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":104,"model":"Multi-Task Light-Weight-RefineNet","metrics":{"Mean IoU":"42.0%"},"uses_additional_data":false,"paper_date":"2018-09-13","paper":"/paper/real-time-joint-semantic-segmentation-and","paper_url":"http://arxiv.org/abs/1809.04766v2","paper_title":"Real-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric Annotations","code":"https://github.com/DrSleep/multi-task-refinenet","n_code_links":4,"official":{"repos":["DrSleep/multi-task-refinenet"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":6,"n_constructed":0,"n_ran_checked":0,"n_instrument":6,"n_unverified":0,"n_samples":6,"n_pointer_only_licence":6,"sample_list":"/paper/real-time-joint-semantic-segmentation-and#ran","syntology_url":"https://syntology.ai/paper/1809.04766","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.04766"}}}},{"rank_in_archive_order":105,"model":"Light-Weight-RefineNet-50","metrics":{"Mean IoU":"41.7%"},"uses_additional_data":false,"paper_date":"2018-10-08","paper":"/paper/light-weight-refinenet-for-real-time-semantic","paper_url":"http://arxiv.org/abs/1810.03272v1","paper_title":"Light-Weight RefineNet for Real-Time Semantic Segmentation","code":"https://github.com/DrSleep/light-weight-refinenet","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":106,"model":"PGT (Swin-T)","metrics":{"Mean IoU":"41.61"},"uses_additional_data":false,"paper_date":"2023-07-28","paper":"/paper/prompt-guided-transformer-for-multi-task","paper_url":"https://arxiv.org/abs/2307.15362v1","paper_title":"Prompt Guided Transformer for Multi-Task Dense Prediction","code":"https://github.com/innovator-zero/MTDP_Lib","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":107,"model":"MTML","metrics":{"Mean IoU":"41.51%"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/multi-task-meta-learning-learn-how-to-adapt","paper_url":"https://arxiv.org/abs/2210.06989v4","paper_title":"Multi-Task Meta Learning: learn how to adapt to unseen tasks","code":"https://github.com/ricupa/mtml-learn-how-to-adapt-to-unseen-tasks","n_code_links":1,"official":{"repos":["ricupa/mtml-learn-how-to-adapt-to-unseen-tasks"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/multi-task-meta-learning-learn-how-to-adapt#ran","syntology_url":"https://syntology.ai/paper/2210.06989","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06989"}}}},{"rank_in_archive_order":108,"model":"RAN","metrics":{"Mean IoU":"41.2%"},"uses_additional_data":false,"paper_date":"2017-07-20","paper":"/paper/semantic-segmentation-with-reverse-attention","paper_url":"http://arxiv.org/abs/1707.06426v1","paper_title":"Semantic Segmentation with Reverse Attention","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":109,"model":"DenseMTL","metrics":{"Mean IoU":"40.84%"},"uses_additional_data":false,"paper_date":"2022-06-17","paper":"/paper/cross-task-attention-mechanism-for-dense","paper_url":"https://arxiv.org/abs/2206.08927v2","paper_title":"DenseMTL: Cross-task Attention Mechanism for Dense Multi-task Learning","code":"https://github.com/astra-vision/densemtl","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":110,"model":"STD2P","metrics":{"Mean IoU":"40.1%"},"uses_additional_data":false,"paper_date":"2016-04-08","paper":"/paper/std2p-rgbd-semantic-segmentation-using-spatio","paper_url":"http://arxiv.org/abs/1604.02388v3","paper_title":"STD2P: RGBD Semantic Segmentation Using Spatio-Temporal Data-Driven Pooling","code":"https://github.com/SSAW14/STD2P","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":111,"model":"MaskSup","metrics":{"Mean IoU":"39.31%"},"uses_additional_data":false,"paper_date":"2022-10-03","paper":"/paper/masked-supervised-learning-for-semantic","paper_url":"https://arxiv.org/abs/2210.00923v2","paper_title":"Masked Supervised Learning for Semantic Segmentation","code":"https://github.com/hasibzunair/masksup-segmentation","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":112,"model":"HeMIS","metrics":{"Mean IoU":"37.77%"},"uses_additional_data":false,"paper_date":"2016-07-18","paper":"/paper/hemis-hetero-modal-image-segmentation","paper_url":"http://arxiv.org/abs/1607.05194v1","paper_title":"HeMIS: Hetero-Modal Image Segmentation","code":"https://github.com/momih/pc-hemis","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":113,"model":"TD4-PSP18","metrics":{"Mean IoU":"37.4"},"uses_additional_data":false,"paper_date":"2020-04-03","paper":"/paper/temporally-distributed-networks-for-fast","paper_url":"https://arxiv.org/abs/2004.01800v2","paper_title":"Temporally Distributed Networks for Fast Video Semantic Segmentation","code":"https://github.com/feinanshan/TDNet","n_code_links":1,"official":null,"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":2,"sample_list":"/paper/temporally-distributed-networks-for-fast#ran","syntology_url":"https://syntology.ai/paper/2004.01800","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.01800"}}}},{"rank_in_archive_order":114,"model":"Bayesian DenseNet","metrics":{"Mean IoU":"37.3%"},"uses_additional_data":false,"paper_date":"2017-03-15","paper":"/paper/what-uncertainties-do-we-need-in-bayesian","paper_url":"http://arxiv.org/abs/1703.04977v2","paper_title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","code":"https://github.com/kyle-dorman/bayesian-neural-network-blogpost","n_code_links":11,"official":null,"syntology":{"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":4,"sample_list":"/paper/what-uncertainties-do-we-need-in-bayesian#ran","syntology_url":"https://syntology.ai/paper/1703.04977","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.04977"}}}},{"rank_in_archive_order":115,"model":"HN-network","metrics":{"Mean IoU":"33.49%"},"uses_additional_data":false,"paper_date":"2020-02-06","paper":"/paper/rgb-based-semantic-segmentation-using-self","paper_url":"https://arxiv.org/abs/2002.02200v1","paper_title":"RGB-based Semantic Segmentation Using Self-Supervised Depth Pre-Training","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":116,"model":"CompL","metrics":{"Mean IoU":"33.48%"},"uses_additional_data":false,"paper_date":"2022-10-13","paper":"/paper/composite-learning-for-robust-and-effective","paper_url":"https://arxiv.org/abs/2210.07239v1","paper_title":"Composite Learning for Robust and Effective Dense Predictions","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":117,"model":"Dilated FCN-2s RGB","metrics":{"Mean IoU":"32.3%"},"uses_additional_data":false,"paper_date":"2017-07-26","paper":"/paper/efficient-yet-deep-convolutional-neural","paper_url":"http://arxiv.org/abs/1707.08254v3","paper_title":"Efficient Yet Deep Convolutional Neural Networks for Semantic Segmentation","code":"https://github.com/SharifAmit/DilatedFCNSegmentation","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":118,"model":"AdaShare","metrics":{"Mean IoU":"29.6%"},"uses_additional_data":false,"paper_date":"2019-11-27","paper":"/paper/adashare-learning-what-to-share-for-efficient","paper_url":"https://arxiv.org/abs/1911.12423v2","paper_title":"AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning","code":"https://github.com/sunxm2357/AdaShare","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":119,"model":"EDNAS+JAReD","metrics":{"Mean IoU":"22.1%"},"uses_additional_data":false,"paper_date":"2022-10-04","paper":"/paper/toward-edge-efficient-dense-predictions-with","paper_url":"https://arxiv.org/abs/2210.01384v1","paper_title":"Toward Edge-Efficient Dense Predictions with Synergistic Multi-Task Neural Architecture Search","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":120,"model":"Cross-stitch","metrics":{"Mean IoU":"19.3%"},"uses_additional_data":false,"paper_date":"2016-04-12","paper":"/paper/cross-stitch-networks-for-multi-task-learning","paper_url":"http://arxiv.org/abs/1604.03539v1","paper_title":"Cross-stitch Networks for Multi-task Learning","code":"https://github.com/helloyide/Cross-stitch-Networks-for-Multi-task-Learning","n_code_links":4,"official":null,"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/cross-stitch-networks-for-multi-task-learning#ran","syntology_url":"https://syntology.ai/paper/1604.03539","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.03539"}}}},{"rank_in_archive_order":121,"model":"FCN-32s RGB-HHA","metrics":{"Mean Accuracy":"44"},"uses_additional_data":false,"paper_date":"2016-05-20","paper":"/paper/fully-convolutional-networks-for-semantic","paper_url":"http://arxiv.org/abs/1605.06211v1","paper_title":"Fully Convolutional Networks for Semantic Segmentation","code":"https://github.com/pytorch/vision","n_code_links":37,"official":null,"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,"adjudicator":"Claude Opus 5.5","adjudicator_from":"groundwork/59_code_with_papers/LB_EXTRACTOR_PREREG.md (not recorded in lb_measurement.json; the file's frozen_commit, measured_on and counts equal the run the pre-registration records)","adjudicator_sensitivity":[69,70],"adjudicator_specificity":[101,103],"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication by a model (adjudicator) of accepted entries on a held-out split of archive papers, rules frozen before the test; adjudicator_sensitivity and adjudicator_specificity are its own controls as [judged right, of]; it was not measured on the newer papers placed here","measurement_sentence":"Measured before publishing, on held-out archive papers: the extractor was given 883 of them and produced output for 881 (the other 2 had no title and were excluded before any model call, so they are not part of this measurement). A model adjudicator (Claude Opus 5.5), blind to which entries were real, judged 108 of 110 accepted entries correct on those held-out archive papers; its own controls: 69 of 70 archive-confirmed entries judged true, 101 of 103 corrupted copies judged false. It was not measured on the newer papers whose results are placed on this site.","coverage":{"sentence":"Syntology has checked 8,886 of the 18,637 papers on this site that are newer than the archive (for 3,717 of them no archive leaderboard matched the paper's tables, so there was nothing further to check); 733 were read and have nothing to place (arXiv has no HTML version of the paper, or that version has no tables), 41 could not be read (the extractor's reply could not be parsed), and results from the other 8,977 appear after they are checked.","complete":false,"papers_newer_than_archive":18637,"papers_checked":8886,"papers_checked_no_leaderboard_matched":3717,"papers_read_nothing_to_place":733,"papers_could_not_be_read":41,"papers_could_not_be_read_by_status":{"unparseable":41},"papers_extracted_not_yet_verified":0,"boards_without_verdict":3,"papers_not_yet_extracted":8975},"board_status":{"sentence":"Of the 8,888 newer papers whose tables Syntology has read (8,886 checked in full and 2 with a leaderboard still awaiting a verdict), none had this board among the leaderboards the extractor considered for their tables yet (it keeps at most 10 boards per paper and 4 per dataset; the lists of 1,596 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), so none await a verdict here.","note":"papers, from the extractor's own records, over the newer papers whose tables were read; proposed = no_cell_passed_checks + rejected_by_independent_check + accepted_not_placed + awaiting_verdict + placed; counts, never a rate","eligible":true,"eligible_note":"false when the extractor never considers this board: it loads only boards with archive rows and at least one metric column (lb_extract.py Boards), so no newer paper can be proposed here; archive_rows and metric_columns say which","archive_rows":121,"metric_columns":2,"papers_read":8888,"papers_read_checked":8886,"papers_read_awaiting_verdict":2,"papers_read_verified":8888,"papers_read_not_yet_verified":0,"papers_read_at_candidate_cap":1596,"papers_read_list_full_without_this_board":1596,"candidates":0,"candidates_capped_note":"candidates = papers that had this board among the leaderboards the extractor considered for their tables; the extractor keeps at most 10 per paper and 4 per dataset, so a board crowded out of a paper's list is not counted and candidates is a floor; papers_read_list_full_without_this_board counts the read papers whose list did not hold this board and had reached 10, or held 4 boards of this board's dataset (the only papers that could have crowded it out); papers_read_at_candidate_cap counts, over every board, the papers whose list reached 10","proposed":0,"no_cell_passed_checks":0,"rejected_by_independent_check":0,"accepted_not_placed":0,"awaiting_verdict":0,"placed":0,"placed_entries_listed":0,"file_lines_unreadable_as_read":0,"since_line":"Since the archive (Syntology): none placed; no newer paper judged to report on this board so far"},"judged_to_report":{"heading":"Newer papers whose tables a model judged to report on this benchmark (a model's judgement, not a result; newest first by arXiv id)","judged_by":{"model":"a model","models_as_recorded":[],"a_record_without_a_model":false,"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here","order":"newest first by arXiv id (the identifier's order, not a rank)","outcomes":{"placed":"placed","no_cell_passed_checks":"no cell passed the extractor's checks","refused_by_rule":"refused by a rule","rejected":"rejected by the independent check","accepted_not_placed":"accepted by the independent check but not placed by this site","awaiting":"awaiting a verdict"},"reason_note":"for refused_by_rule, the rules' plain words for the reason codes the record gives (never the quoted or the actual cell text); null for every other outcome","total":0,"shown_on_page":0,"no_cell_split":{"no_cell_passed_checks_in_ledger":0,"rows_refused_by_rule":0,"rows_no_cell_passed_checks":0},"rows":[]},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per row: of M harvested code samples from that row's paper, n_ran executed on a synthesized fixture (n_ran = n_ran_checked + n_instrument; n_instrument counts failures of Syntology's instrument, not of the code); the other M - n_ran 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).","key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"rows_with_graph_line":38,"rows_with_any_sample_ran":34,"rows_with_a_run_with_no_instrument_failure":30,"official":{"state_rule":"the archive's official repositories have samples for this paper that ran: 'official (archive's flag): N ran' (N counts them, instrument failures included); they have samples, none ran: 'official: harvested, nothing ran'; they have no sample for this paper and another sample ran: 'community repositories only' when every sample that ran came from a repository the archive lists for the paper but neither marks official nor records as mentioned in it, or one Syntology harvested outside the archive's links, else 'official: no sample here; runs from other or unrecorded repositories' (a repository named in the paper or found in its text by Syntology, or no repository recorded); otherwise 'official: harvested for another paper' or 'official: not harvested'. Absent when the archive marks no repository official. Official is the archive's is_official flag, not an authorship verdict","flag":"the archive's is_official flag for the paper's code link; not a verdict on who wrote the code","rows_with_an_archive_official_repository":33,"rows_whose_official_repository_has_a_sample_that_ran":26,"rows_whose_official_repository_has_a_run_with_no_instrument_failure":23,"rows_community_repositories_only":3,"rows_runs_from_other_or_unrecorded_repositories":0,"note":"rows[].official, per row with a graph line: repos (marked official in the archive), state, n_ran and n_unverified (samples from those repositories), and ran_from_kinds (the kinds of repository the paper's samples that ran came from; 'unlocated' is no repository recorded)"},"filters":{"ran_modes":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"the page's filters hide rows and never renumber them; they read the Ran cell's counts, the same figures rows[].syntology and rows[].official carry"},"row_route":"rows[].syntology carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","distinct_papers_with_graph_line":25,"distinct_papers_with_any_sample_ran":23,"distinct_papers_with_a_run_with_no_instrument_failure":19,"samples_over_distinct_papers":{"n_ran":111,"n_constructed":6,"n_ran_checked":85,"n_instrument":26,"n_unverified":54,"n_samples":165,"n_pointer_only_licence":29,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":160,"n_constructed":8,"n_ran_checked":123,"n_instrument":37,"n_unverified":77,"n_samples":237,"n_pointer_only_licence":36,"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"}},"record_sha256":"6f0dfb707dc3b024cb112f83dfb69fc38d1ec0643d210d6644e072248052b034","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}