{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/cmx-cross-modal-fusion-for-rgb-x-semantic","title":"CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers","arxiv_id":"2203.04838","date":"2022-03-09","proceeding":null,"authors":["Jiaming Zhang","Huayao Liu","Kailun Yang","Xinxin Hu","Ruiping Liu","Rainer Stiefelhagen"],"abstract":"Scene understanding based on image segmentation is a crucial component of autonomous vehicles. Pixel-wise semantic segmentation of RGB images can be advanced by exploiting complementary features from the supplementary modality (X-modality). However, covering a wide variety of sensors with a modality-agnostic model remains an unresolved problem due to variations in sensor characteristics among different modalities. Unlike previous modality-specific methods, in this work, we propose a unified fusion framework, CMX, for RGB-X semantic segmentation. To generalize well across different modalities, that often include supplements as well as uncertainties, a unified cross-modal interaction is crucial for modality fusion. Specifically, we design a Cross-Modal Feature Rectification Module (CM-FRM) to calibrate bi-modal features by leveraging the features from one modality to rectify the features of the other modality. With rectified feature pairs, we deploy a Feature Fusion Module (FFM) to perform sufficient exchange of long-range contexts before mixing. To verify CMX, for the first time, we unify five modalities complementary to RGB, i.e., depth, thermal, polarization, event, and LiDAR. Extensive experiments show that CMX generalizes well to diverse multi-modal fusion, achieving state-of-the-art performances on five RGB-Depth benchmarks, as well as RGB-Thermal, RGB-Polarization, and RGB-LiDAR datasets. Besides, to investigate the generalizability to dense-sparse data fusion, we establish an RGB-Event semantic segmentation benchmark based on the EventScape dataset, on which CMX sets the new state-of-the-art. The source code of CMX is publicly available at https://github.com/huaaaliu/RGBX_Semantic_Segmentation.","url_abs":"https://arxiv.org/abs/2203.04838v5","url_pdf":"https://arxiv.org/pdf/2203.04838v5.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"cmx-cross-modal-fusion-for-rgb-x-semantic","repo_url":"https://github.com/huaaaliu/rgbx_semantic_segmentation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-object-detection","task_name":"3D Object Detection"},{"task_slug":"autonomous-vehicles","task_name":"Autonomous Vehicles"},{"task_slug":"camouflaged-object-segmentation","task_name":"Camouflaged Object Segmentation"},{"task_slug":"image-manipulation-localization","task_name":"Image Manipulation Localization"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"multispectral-object-detection","task_name":"Multispectral Object Detection"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"pedestrian-detection","task_name":"Pedestrian Detection"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"thermal-image-segmentation","task_name":"Thermal Image Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/camouflaged-object-segmentation-on-pcod-1200","task":"Camouflaged Object Segmentation","dataset":"PCOD_1200","model":"CMX","rank_in_archive_order":1,"of":16,"metrics":{"S-Measure":"0.922"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-localization-on-coverage","task":"Image Manipulation Localization","dataset":"COVERAGE","model":"CMX (RGB+SRM)","rank_in_archive_order":3,"of":11,"metrics":{"Average Pixel F1(Fixed threshold)":".630"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-localization-on-coverage","task":"Image Manipulation Localization","dataset":"COVERAGE","model":"CMX (RGB+Bayar)","rank_in_archive_order":5,"of":11,"metrics":{"Average Pixel F1(Fixed threshold)":".592"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-localization-on-coverage","task":"Image Manipulation Localization","dataset":"COVERAGE","model":"CMX (RGB+NP++)","rank_in_archive_order":6,"of":11,"metrics":{"Average Pixel F1(Fixed threshold)":".577"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-localization-on-casia-v1","task":"Image Manipulation Localization","dataset":"Casia V1+","model":"CMX (RGB+SRM)","rank_in_archive_order":1,"of":11,"metrics":{"Average Pixel F1(Fixed threshold)":".791"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-localization-on-casia-v1","task":"Image Manipulation Localization","dataset":"Casia V1+","model":"CMX (RGB+Bayar)","rank_in_archive_order":4,"of":11,"metrics":{"Average Pixel F1(Fixed threshold)":".774"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-localization-on-casia-v1","task":"Image Manipulation Localization","dataset":"Casia V1+","model":"CMX (RGB+NP++)","rank_in_archive_order":5,"of":11,"metrics":{"Average Pixel F1(Fixed threshold)":".761"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-localization-on-cocoglide","task":"Image Manipulation Localization","dataset":"CocoGlide","model":"CMX (RGB+SRM)","rank_in_archive_order":1,"of":11,"metrics":{"Average Pixel F1(Fixed threshold)":".585"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-localization-on-cocoglide","task":"Image Manipulation Localization","dataset":"CocoGlide","model":"CMX (RGB+Bayar)","rank_in_archive_order":3,"of":11,"metrics":{"Average Pixel F1(Fixed threshold)":".566"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-localization-on-cocoglide","task":"Image Manipulation Localization","dataset":"CocoGlide","model":"CMX (RGB+NP++)","rank_in_archive_order":7,"of":11,"metrics":{"Average Pixel F1(Fixed threshold)":".516"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-localization-on-columbia","task":"Image Manipulation Localization","dataset":"Columbia","model":"CMX (RGB+NP++)","rank_in_archive_order":2,"of":11,"metrics":{"Average Pixel F1(Fixed threshold)":".884"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-localization-on-columbia","task":"Image Manipulation Localization","dataset":"Columbia","model":"CMX (RGB+Bayar)","rank_in_archive_order":3,"of":11,"metrics":{"Average Pixel F1(Fixed threshold)":".872"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-localization-on-columbia","task":"Image Manipulation Localization","dataset":"Columbia","model":"CMX (RGB+SRM)","rank_in_archive_order":7,"of":11,"metrics":{"Average Pixel F1(Fixed threshold)":".834"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-localization-on-dso-1","task":"Image Manipulation Localization","dataset":"DSO-1","model":"CMX (RGB+NP++)","rank_in_archive_order":3,"of":11,"metrics":{"Average Pixel F1(Fixed threshold)":".895"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-localization-on-dso-1","task":"Image Manipulation Localization","dataset":"DSO-1","model":"CMX (RGB+SRM)","rank_in_archive_order":5,"of":11,"metrics":{"Average Pixel F1(Fixed threshold)":".792"},"uses_additional_data":false},{"leaderboard":"/sota/image-manipulation-localization-on-dso-1","task":"Image Manipulation Localization","dataset":"DSO-1","model":"CMX (RGB+Bayar)","rank_in_archive_order":6,"of":11,"metrics":{"Average Pixel F1(Fixed threshold)":".776"},"uses_additional_data":false},{"leaderboard":"/sota/multispectral-object-detection-on-flir-1","task":"Multispectral Object Detection","dataset":"FLIR","model":"CMX","rank_in_archive_order":5,"of":18,"metrics":{"mAP50":"82.2%"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-dsec","task":"Object Detection","dataset":"DSEC","model":"CMX","rank_in_archive_order":4,"of":12,"metrics":{"mAP":"29.1"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-eventped","task":"Object Detection","dataset":"EventPed","model":"CMX","rank_in_archive_order":4,"of":6,"metrics":{"AP":"58.0"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-inoutdoor","task":"Object Detection","dataset":"InOutDoor","model":"CMX","rank_in_archive_order":3,"of":6,"metrics":{"AP":"62.3"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-pku-ddd17-car","task":"Object Detection","dataset":"PKU-DDD17-Car","model":"CMX","rank_in_archive_order":12,"of":14,"metrics":{"mAP50":"80.4"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-stcrowd","task":"Object Detection","dataset":"STCrowd","model":"CMX","rank_in_archive_order":3,"of":6,"metrics":{"AP":"61.0"},"uses_additional_data":false},{"leaderboard":"/sota/pedestrian-detection-on-cvc14","task":"Pedestrian Detection","dataset":"CVC14","model":"CMX","rank_in_archive_order":2,"of":2,"metrics":{"AP50":"68.9"},"uses_additional_data":false},{"leaderboard":"/sota/pedestrian-detection-on-dvtod","task":"Pedestrian Detection","dataset":"DVTOD","model":"CMX","rank_in_archive_order":4,"of":8,"metrics":{" mAP":"81.6"},"uses_additional_data":false},{"leaderboard":"/sota/pedestrian-detection-on-llvip","task":"Pedestrian Detection","dataset":"LLVIP","model":"CMX","rank_in_archive_order":7,"of":15,"metrics":{"AP":"0.596"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-bjroad","task":"Semantic Segmentation","dataset":"BJRoad","model":"CMX","rank_in_archive_order":3,"of":11,"metrics":{"IoU":"62.28"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-cityscapes-val","task":"Semantic Segmentation","dataset":"Cityscapes val","model":"CMX (B4)","rank_in_archive_order":34,"of":99,"metrics":{"mIoU":"82.6"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-cityscapes-val","task":"Semantic Segmentation","dataset":"Cityscapes val","model":"CMX (B2)","rank_in_archive_order":41,"of":99,"metrics":{"mIoU":"81.6"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-ddd17","task":"Semantic Segmentation","dataset":"DDD17","model":"CMX","rank_in_archive_order":3,"of":9,"metrics":{"mIoU":"71.88"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-dsec","task":"Semantic Segmentation","dataset":"DSEC","model":"CMX","rank_in_archive_order":3,"of":9,"metrics":{"mIoU":"72.42"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-deliver","task":"Semantic Segmentation","dataset":"DeLiVER","model":"CMX (RGB-Depth)","rank_in_archive_order":10,"of":26,"metrics":{"mIoU":"62.67"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-deliver","task":"Semantic Segmentation","dataset":"DeLiVER","model":"CMX (RGB-Event)","rank_in_archive_order":15,"of":26,"metrics":{"mIoU":"56.52"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-deliver","task":"Semantic Segmentation","dataset":"DeLiVER","model":"CMX (RGB-LiDAR)","rank_in_archive_order":16,"of":26,"metrics":{"mIoU":"56.37"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-event-based","task":"Semantic Segmentation","dataset":"Event-based Segmentation Dataset","model":"CMX","rank_in_archive_order":2,"of":6,"metrics":{"mIoU":"85.81"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-eventscape","task":"Semantic Segmentation","dataset":"EventScape","model":"CMX (B4)","rank_in_archive_order":1,"of":12,"metrics":{"mIoU":"64.28"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-eventscape","task":"Semantic Segmentation","dataset":"EventScape","model":"CMX (B2)","rank_in_archive_order":2,"of":12,"metrics":{"mIoU":"61.90"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-gamus","task":"Semantic Segmentation","dataset":"GAMUS","model":"CMX","rank_in_archive_order":2,"of":6,"metrics":{"mIoU":"75.23"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-kitti-360","task":"Semantic Segmentation","dataset":"KITTI-360","model":"CMX (RGB-Depth)","rank_in_archive_order":5,"of":17,"metrics":{"mIoU":"64.43"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-kitti-360","task":"Semantic Segmentation","dataset":"KITTI-360","model":"CMX (RGB-LiDAR)","rank_in_archive_order":6,"of":17,"metrics":{"mIoU":"64.31"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-llrgbd-synthetic","task":"Semantic Segmentation","dataset":"LLRGBD-synthetic","model":"CMX (SegFormer-B2)","rank_in_archive_order":3,"of":8,"metrics":{"mIoU":"66.52"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-nyu-depth-v2","task":"Semantic Segmentation","dataset":"NYU Depth v2","model":"CMX (B5)","rank_in_archive_order":17,"of":121,"metrics":{"Mean IoU":"56.9%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-nyu-depth-v2","task":"Semantic Segmentation","dataset":"NYU Depth v2","model":"CMX (B4)","rank_in_archive_order":21,"of":121,"metrics":{"Mean IoU":"56.3%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-nyu-depth-v2","task":"Semantic Segmentation","dataset":"NYU Depth v2","model":"CMX (B2)","rank_in_archive_order":30,"of":121,"metrics":{"Mean IoU":"54.4%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-porto","task":"Semantic Segmentation","dataset":"Porto","model":"CMX","rank_in_archive_order":2,"of":6,"metrics":{"IoU":"72.85"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-potsdam","task":"Semantic Segmentation","dataset":"Potsdam","model":"CMX","rank_in_archive_order":2,"of":11,"metrics":{"mIoU":"85.97"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-replica","task":"Semantic Segmentation","dataset":"Replica","model":"CMX","rank_in_archive_order":5,"of":5,"metrics":{"mIoU":"17.0"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-selma","task":"Semantic Segmentation","dataset":"SELMA","model":"CMX","rank_in_archive_order":1,"of":7,"metrics":{"mIoU":"91.7"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-sun-rgbd","task":"Semantic Segmentation","dataset":"SUN-RGBD","model":"CMX (B5)","rank_in_archive_order":11,"of":44,"metrics":{"Mean IoU":"52.4%"},"uses_additional_data":true},{"leaderboard":"/sota/semantic-segmentation-on-sun-rgbd","task":"Semantic Segmentation","dataset":"SUN-RGBD","model":"CMX (B4)","rank_in_archive_order":12,"of":44,"metrics":{"Mean IoU":"52.1%"},"uses_additional_data":true},{"leaderboard":"/sota/semantic-segmentation-on-sun-rgbd","task":"Semantic Segmentation","dataset":"SUN-RGBD","model":"DPLNet","rank_in_archive_order":20,"of":44,"metrics":{"Mean IoU":"49.7%"},"uses_additional_data":true},{"leaderboard":"/sota/semantic-segmentation-on-syn-udtiri","task":"Semantic Segmentation","dataset":"SYN-UDTIRI","model":"CMX","rank_in_archive_order":3,"of":10,"metrics":{"IoU":"93.31"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-scannetv2","task":"Semantic Segmentation","dataset":"ScanNetV2","model":"CMX","rank_in_archive_order":1,"of":12,"metrics":{"Mean IoU":"61.3%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-spectralwaste","task":"Semantic Segmentation","dataset":"SpectralWaste","model":"CMX (RGB-HYPER)","rank_in_archive_order":1,"of":8,"metrics":{"mIoU":"58.2"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-spectralwaste","task":"Semantic Segmentation","dataset":"SpectralWaste","model":"CMX ( RGB-HYPER3 )","rank_in_archive_order":2,"of":8,"metrics":{"mIoU":"56.6"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-stanford2d3d-rgbd","task":"Semantic Segmentation","dataset":"Stanford2D3D - RGBD","model":"CMX (SegFormer-B4)","rank_in_archive_order":1,"of":6,"metrics":{"Pixel Accuracy":"82.6","mIoU":"62.1"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-stanford2d3d-rgbd","task":"Semantic Segmentation","dataset":"Stanford2D3D - RGBD","model":"CMX (SegFormer-B2)","rank_in_archive_order":2,"of":6,"metrics":{"Pixel Accuracy":"82.3","mIoU":"61.2"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-synthetic-bathing","task":"Semantic Segmentation","dataset":"Synthetic Bathing Perception","model":"CMX-SRA","rank_in_archive_order":1,"of":5,"metrics":{"mIoU":"94.20"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-synthetic-bathing","task":"Semantic Segmentation","dataset":"Synthetic Bathing Perception","model":"CMX","rank_in_archive_order":2,"of":5,"metrics":{"mIoU":"88.23"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-tlcgis","task":"Semantic Segmentation","dataset":"TLCGIS","model":"CMX","rank_in_archive_order":2,"of":6,"metrics":{"IoU":"84.14"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-uplight","task":"Semantic Segmentation","dataset":"UPLight","model":"CMX (B2 RGB-AoLP)","rank_in_archive_order":2,"of":8,"metrics":{"mIoU":"92.13"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-uplight","task":"Semantic Segmentation","dataset":"UPLight","model":"CMX (B2 RGB-DoLP)","rank_in_archive_order":3,"of":8,"metrics":{"mIoU":"92.07"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-us3d","task":"Semantic Segmentation","dataset":"US3D","model":"CMX","rank_in_archive_order":2,"of":11,"metrics":{"mIoU":"84.63"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-vaihingen","task":"Semantic Segmentation","dataset":"Vaihingen","model":"CMX","rank_in_archive_order":1,"of":13,"metrics":{"mIoU":"82.87"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-zju-rgb-p","task":"Semantic Segmentation","dataset":"ZJU-RGB-P","model":"CMX (B4 RGB-AoLP)","rank_in_archive_order":4,"of":13,"metrics":{"mIoU":"92.6"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-zju-rgb-p","task":"Semantic Segmentation","dataset":"ZJU-RGB-P","model":"CMX (B2 RGB-DoLP)","rank_in_archive_order":6,"of":13,"metrics":{"mIoU":"92.2"},"uses_additional_data":false},{"leaderboard":"/sota/thermal-image-segmentation-on-kp-day-night","task":"Thermal Image Segmentation","dataset":"KP day-night","model":"CMX","rank_in_archive_order":3,"of":5,"metrics":{"mIoU":"46.2"},"uses_additional_data":false},{"leaderboard":"/sota/thermal-image-segmentation-on-mfn-dataset","task":"Thermal Image Segmentation","dataset":"MFN Dataset","model":"CMX (B4)","rank_in_archive_order":7,"of":55,"metrics":{"mIOU":"59.7"},"uses_additional_data":false},{"leaderboard":"/sota/thermal-image-segmentation-on-mfn-dataset","task":"Thermal Image Segmentation","dataset":"MFN Dataset","model":"CMX (B2)","rank_in_archive_order":15,"of":55,"metrics":{"mIOU":"58.2"},"uses_additional_data":false},{"leaderboard":"/sota/thermal-image-segmentation-on-noisy-rs-rgb-t","task":"Thermal Image Segmentation","dataset":"Noisy RS RGB-T Dataset","model":"CMX (B4)","rank_in_archive_order":3,"of":6,"metrics":{"mIoU":"56.1"},"uses_additional_data":false},{"leaderboard":"/sota/thermal-image-segmentation-on-rgb-t-glass","task":"Thermal Image Segmentation","dataset":"RGB-T-Glass-Segmentation","model":"CMX","rank_in_archive_order":2,"of":22,"metrics":{"MAE":"0.029"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2203.04838","atlas_url":"https://app.syntology.ai/?focus=2203.04838","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.04838"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/huaaaliu/rgbx_semantic_segmentation","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"83ca13ec3eefbcd1","entry":"random_mirror","repo":"huaaaliu/rgbx_semantic_segmentation","repo_kind":"official","path":"dataloader/dataloader.py","file_url":"https://github.com/huaaaliu/rgbx_semantic_segmentation/blob/HEAD/dataloader/dataloader.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"83ca13ec3eefbcd1"}},{"code_sha256_prefix":"3e2c98e28bc11bd4","entry":"random_scale","repo":"huaaaliu/rgbx_semantic_segmentation","repo_kind":"official","path":"dataloader/dataloader.py","file_url":"https://github.com/huaaaliu/rgbx_semantic_segmentation/blob/HEAD/dataloader/dataloader.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3e2c98e28bc11bd4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}