{"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-cityscapes","task":{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","note":null},"dataset":{"name":"Cityscapes test","url":"/dataset/cityscapes"},"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 (class)","Category mIoU"],"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 (class)":"higher","Category mIoU":null}},"counts":{"rows":105,"rows_with_code":97,"rows_with_paper_page":105,"rows_dated":105,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"VLTSeg","metrics":{"Mean IoU (class)":"86.4"},"uses_additional_data":false,"paper_date":"2023-12-04","paper":"/paper/vltseg-simple-transfer-of-clip-based-vision","paper_url":"https://arxiv.org/abs/2312.02021v4","paper_title":"Strong but simple: A Baseline for Domain Generalized Dense Perception by CLIP-based Transfer Learning","code":"https://github.com/VLTSeg/VLTSeg","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":2,"model":"MetaPrompt-SD","metrics":{"Mean IoU (class)":"86.2"},"uses_additional_data":false,"paper_date":"2023-12-22","paper":"/paper/harnessing-diffusion-models-for-visual","paper_url":"https://arxiv.org/abs/2312.14733v1","paper_title":"Harnessing Diffusion Models for Visual Perception with Meta Prompts","code":"https://github.com/fudan-zvg/meta-prompts","n_code_links":1,"official":{"repos":["fudan-zvg/meta-prompts"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_samples":6,"n_pointer_only_licence":4,"sample_list":"/paper/harnessing-diffusion-models-for-visual#ran","syntology_url":"https://syntology.ai/paper/2312.14733","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.14733"}}}},{"rank_in_archive_order":3,"model":"InternImage-H","metrics":{"Mean IoU (class)":"86.1%"},"uses_additional_data":false,"paper_date":"2022-11-10","paper":"/paper/internimage-exploring-large-scale-vision","paper_url":"https://arxiv.org/abs/2211.05778v4","paper_title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","code":"https://github.com/opengvlab/internimage","n_code_links":3,"official":{"repos":["opengvlab/internimage"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":0,"sample_list":"/paper/internimage-exploring-large-scale-vision#ran","syntology_url":"https://syntology.ai/paper/2211.05778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.05778"}}}},{"rank_in_archive_order":4,"model":"HS3-Fuse","metrics":{"Mean IoU (class)":"85.8%"},"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":5,"model":"InverseForm","metrics":{"Mean IoU (class)":"85.6%"},"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":6,"model":"ViT-Adapter-L (Mask2Former, BEiT pretrain)","metrics":{"Mean IoU (class)":"85.2%"},"uses_additional_data":false,"paper_date":"2022-05-17","paper":"/paper/vision-transformer-adapter-for-dense","paper_url":"https://arxiv.org/abs/2205.08534v4","paper_title":"Vision Transformer Adapter for Dense Predictions","code":"https://github.com/czczup/vit-adapter","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":7,"model":"SERNet-Former","metrics":{"Mean IoU (class)":"84.83"},"uses_additional_data":false,"paper_date":"2024-01-28","paper":"/paper/sernet-former-semantic-segmentation-by","paper_url":"https://arxiv.org/abs/2401.15741v7","paper_title":"SERNet-Former: Semantic Segmentation by Efficient Residual Network with Attention-Boosting Gates and Attention-Fusion Networks","code":"https://github.com/serdarch/sernet-former","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":8,"model":"Depth Anything","metrics":{"Mean IoU (class)":"84.8%"},"uses_additional_data":false,"paper_date":"2024-01-19","paper":"/paper/depth-anything-unleashing-the-power-of-large","paper_url":"https://arxiv.org/abs/2401.10891v2","paper_title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","code":"https://github.com/LiheYoung/Depth-Anything","n_code_links":7,"official":{"repos":["LiheYoung/Depth-Anything"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":2,"n_samples":11,"n_pointer_only_licence":0,"sample_list":"/paper/depth-anything-unleashing-the-power-of-large#ran","syntology_url":"https://syntology.ai/paper/2401.10891","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.10891"}}}},{"rank_in_archive_order":9,"model":"HRNetV2 + OCR +","metrics":{"Mean IoU (class)":"84.5%"},"uses_additional_data":false,"paper_date":"2019-09-24","paper":"/paper/object-contextual-representations-for","paper_url":"https://arxiv.org/abs/1909.11065v6","paper_title":"Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation","code":"https://github.com/open-mmlab/mmsegmentation","n_code_links":11,"official":{"repos":["HRNet/HRNet-Semantic-Segmentation"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":4,"n_samples":9,"n_pointer_only_licence":1,"sample_list":"/paper/object-contextual-representations-for#ran","syntology_url":"https://syntology.ai/paper/1909.11065","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11065"}}}},{"rank_in_archive_order":10,"model":"EfficientPS","metrics":{"Mean IoU (class)":"84.21%"},"uses_additional_data":false,"paper_date":"2020-04-05","paper":"/paper/efficientps-efficient-panoptic-segmentation","paper_url":"https://arxiv.org/abs/2004.02307v3","paper_title":"EfficientPS: Efficient Panoptic Segmentation","code":"https://github.com/DeepSceneSeg/EfficientPS","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":11,"model":"Panoptic-DeepLab","metrics":{"Mean IoU (class)":"84.2%"},"uses_additional_data":false,"paper_date":"2019-11-22","paper":"/paper/panoptic-deeplab-a-simple-strong-and-fast","paper_url":"https://arxiv.org/abs/1911.10194v3","paper_title":"Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation","code":"https://github.com/tensorflow/models/tree/master/official/projects/panoptic","n_code_links":9,"official":{"repos":["bowenc0221/panoptic-deeplab"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed"]},"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":4,"n_samples":9,"n_pointer_only_licence":1,"sample_list":"/paper/panoptic-deeplab-a-simple-strong-and-fast#ran","syntology_url":"https://syntology.ai/paper/1911.10194","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.10194"}}}},{"rank_in_archive_order":12,"model":"HRNetV2 + OCR (w/ ASP)","metrics":{"Mean IoU (class)":"83.7%"},"uses_additional_data":false,"paper_date":"2019-09-24","paper":"/paper/object-contextual-representations-for","paper_url":"https://arxiv.org/abs/1909.11065v6","paper_title":"Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation","code":"https://github.com/open-mmlab/mmsegmentation","n_code_links":11,"official":{"repos":["HRNet/HRNet-Semantic-Segmentation"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":4,"n_samples":9,"n_pointer_only_licence":1,"sample_list":"/paper/object-contextual-representations-for#ran","syntology_url":"https://syntology.ai/paper/1909.11065","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11065"}}}},{"rank_in_archive_order":13,"model":"DCNAS(coarse + Mapillary)","metrics":{"Mean IoU (class)":"83.6%"},"uses_additional_data":false,"paper_date":"2020-03-26","paper":"/paper/dcnas-densely-connected-neural-architecture","paper_url":"https://arxiv.org/abs/2003.11883v2","paper_title":"DCNAS: Densely Connected Neural Architecture Search for Semantic Image Segmentation","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":14,"model":"Euclidean Frank-Wolfe CRFs (backbone: DeepLabv3+)(coarse)","metrics":{"Mean IoU (class)":"83.6%"},"uses_additional_data":false,"paper_date":"2021-10-27","paper":"/paper/regularized-frank-wolfe-for-dense-crfs","paper_url":"https://arxiv.org/abs/2110.14759v2","paper_title":"Regularized Frank-Wolfe for Dense CRFs: Generalizing Mean Field and Beyond","code":"https://github.com/netw0rkf10w/crf","n_code_links":1,"official":{"repos":["netw0rkf10w/crf"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":4,"n_constructed":1,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":0,"sample_list":"/paper/regularized-frank-wolfe-for-dense-crfs#ran","syntology_url":"https://syntology.ai/paper/2110.14759","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.14759"}}}},{"rank_in_archive_order":15,"model":"GALDNet(+Mapillary)++","metrics":{"Mean IoU (class)":"83.3%"},"uses_additional_data":false,"paper_date":"2019-09-16","paper":"/paper/global-aggregation-then-local-distribution-in","paper_url":"https://arxiv.org/abs/1909.07229v1","paper_title":"Global Aggregation then Local Distribution in Fully Convolutional Networks","code":"https://github.com/lxtGH/GALD-DGCNet","n_code_links":2,"official":{"repos":["lxtGH/GALD-Net"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":4,"sample_list":"/paper/global-aggregation-then-local-distribution-in#ran","syntology_url":"https://syntology.ai/paper/1909.07229","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.07229"}}}},{"rank_in_archive_order":16,"model":"ResNeSt200 (Mapillary)","metrics":{"Mean IoU (class)":"83.3%"},"uses_additional_data":false,"paper_date":"2020-04-19","paper":"/paper/resnest-split-attention-networks","paper_url":"https://arxiv.org/abs/2004.08955v2","paper_title":"ResNeSt: Split-Attention Networks","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":36,"official":{"repos":["zhanghang1989/ResNeSt"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":28,"n_constructed":0,"n_ran_checked":21,"n_instrument":7,"n_unverified":20,"n_samples":48,"n_pointer_only_licence":23,"sample_list":"/paper/resnest-split-attention-networks#ran","syntology_url":"https://syntology.ai/paper/2004.08955","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.08955"}}}},{"rank_in_archive_order":17,"model":"HANet (Height-driven Attention Networks by LGE A&B)(coarse)","metrics":{"Mean IoU (class)":"83.2%"},"uses_additional_data":false,"paper_date":"2020-03-11","paper":"/paper/cars-cant-fly-up-in-the-sky-improving-urban","paper_url":"https://arxiv.org/abs/2003.05128v3","paper_title":"Cars Can't Fly up in the Sky: Improving Urban-Scene Segmentation via Height-driven Attention Networks","code":"https://github.com/shachoi/HANet","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":18,"model":"kMaX-DeepLab (ConvNeXt-L, fine only)","metrics":{"Mean IoU (class)":"83.2%"},"uses_additional_data":false,"paper_date":"2022-07-08","paper":"/paper/k-means-mask-transformer","paper_url":"https://arxiv.org/abs/2207.04044v5","paper_title":"kMaX-DeepLab: k-means Mask Transformer","code":"https://github.com/google-research/deeplab2","n_code_links":3,"official":null,"syntology":null},{"rank_in_archive_order":19,"model":"SegFormer (MiT-B5, Mapillary)","metrics":{"Mean IoU (class)":"83.1%"},"uses_additional_data":false,"paper_date":"2021-05-31","paper":"/paper/segformer-simple-and-efficient-design-for","paper_url":"https://arxiv.org/abs/2105.15203v3","paper_title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","code":"https://github.com/huggingface/transformers","n_code_links":28,"official":{"repos":["NVlabs/SegFormer"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community","listed","unlocated"]},"syntology":{"n_ran":66,"n_constructed":22,"n_ran_checked":52,"n_instrument":14,"n_unverified":20,"n_samples":86,"n_pointer_only_licence":20,"sample_list":"/paper/segformer-simple-and-efficient-design-for#ran","syntology_url":"https://syntology.ai/paper/2105.15203","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.15203"}}}},{"rank_in_archive_order":20,"model":"OCR (HRNetV2-W48, coarse)","metrics":{"Mean IoU (class)":"83.0%"},"uses_additional_data":false,"paper_date":"2019-09-24","paper":"/paper/object-contextual-representations-for","paper_url":"https://arxiv.org/abs/1909.11065v6","paper_title":"Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation","code":"https://github.com/open-mmlab/mmsegmentation","n_code_links":11,"official":{"repos":["HRNet/HRNet-Semantic-Segmentation"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":4,"n_samples":9,"n_pointer_only_licence":1,"sample_list":"/paper/object-contextual-representations-for#ran","syntology_url":"https://syntology.ai/paper/1909.11065","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11065"}}}},{"rank_in_archive_order":21,"model":"MRFM(coarse)","metrics":{"Mean IoU (class)":"83.0%"},"uses_additional_data":false,"paper_date":"2020-11-17","paper":"/paper/multi-receptive-field-network-for-semantic","paper_url":"https://arxiv.org/abs/2011.08577v2","paper_title":"Multi Receptive Field Network for Semantic Segmentation","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":22,"model":"DNL (coarse)","metrics":{"Mean IoU (class)":"83%"},"uses_additional_data":false,"paper_date":"2020-06-11","paper":"/paper/disentangled-non-local-neural-networks","paper_url":"https://arxiv.org/abs/2006.06668v2","paper_title":"Disentangled Non-Local Neural Networks","code":"https://github.com/open-mmlab/mmsegmentation","n_code_links":5,"official":{"repos":["Howal/DNL-Object-Detection","yinmh17/DNL-Semantic-Segmentation"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/disentangled-non-local-neural-networks#ran","syntology_url":"https://syntology.ai/paper/2006.06668","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.06668"}}}},{"rank_in_archive_order":23,"model":"DRAN(ResNet-101) WITH ONLY FINE ANNOTATED DATA","metrics":{"Mean IoU (class)":"82.9%"},"uses_additional_data":false,"paper_date":"2020-08-05","paper":"/paper/scene-segmentation-with-dual-relation-aware","paper_url":"https://ieeexplore.ieee.org/document/9154612","paper_title":"Scene Segmentation with Dual Relation-aware Attention Network","code":"https://github.com/junfu1115/DRAN","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":24,"model":"Gated-SCNN","metrics":{"Mean IoU (class)":"82.8%"},"uses_additional_data":false,"paper_date":"2019-07-12","paper":"/paper/gated-scnn-gated-shape-cnns-for-semantic","paper_url":"https://arxiv.org/abs/1907.05740v1","paper_title":"Gated-SCNN: Gated Shape CNNs for Semantic Segmentation","code":"https://github.com/PaddlePaddle/PaddleSeg","n_code_links":4,"official":null,"syntology":null},{"rank_in_archive_order":25,"model":"Dense Prediction Cell","metrics":{"Mean IoU (class)":"82.7%"},"uses_additional_data":false,"paper_date":"2018-09-11","paper":"/paper/searching-for-efficient-multi-scale","paper_url":"http://arxiv.org/abs/1809.04184v1","paper_title":"Searching for Efficient Multi-Scale Architectures for Dense Image Prediction","code":"https://github.com/tensorflow/models","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":26,"model":"CAA (ResNet-101)","metrics":{"Mean IoU (class)":"82.6%"},"uses_additional_data":false,"paper_date":"2021-01-19","paper":"/paper/caa-channelized-axial-attention-for-semantic","paper_url":"https://arxiv.org/abs/2101.07434v5","paper_title":"Channelized Axial Attention for Semantic Segmentation -- Considering Channel Relation within Spatial Attention for Semantic Segmentation","code":"https://github.com/edwardyehuang/CAA","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":27,"model":"OCR (ResNet-101, coarse)","metrics":{"Mean IoU (class)":"82.4%"},"uses_additional_data":false,"paper_date":"2019-09-24","paper":"/paper/object-contextual-representations-for","paper_url":"https://arxiv.org/abs/1909.11065v6","paper_title":"Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation","code":"https://github.com/open-mmlab/mmsegmentation","n_code_links":11,"official":{"repos":["HRNet/HRNet-Semantic-Segmentation"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":4,"n_samples":9,"n_pointer_only_licence":1,"sample_list":"/paper/object-contextual-representations-for#ran","syntology_url":"https://syntology.ai/paper/1909.11065","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11065"}}}},{"rank_in_archive_order":28,"model":"DDRNet-39 1.5x","metrics":{"Mean IoU (class)":"82.4%"},"uses_additional_data":false,"paper_date":"2021-01-15","paper":"/paper/deep-dual-resolution-networks-for-real-time","paper_url":"https://arxiv.org/abs/2101.06085v2","paper_title":"Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes","code":"https://github.com/Deci-AI/super-gradients","n_code_links":8,"official":null,"syntology":null},{"rank_in_archive_order":29,"model":"SSMA","metrics":{"Mean IoU (class)":"82.3%"},"uses_additional_data":false,"paper_date":"2018-08-11","paper":"/paper/self-supervised-model-adaptation-for","paper_url":"https://arxiv.org/abs/1808.03833v3","paper_title":"Self-Supervised Model Adaptation for Multimodal Semantic Segmentation","code":"https://github.com/DeepSceneSeg/SSMA","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":30,"model":"Gated Fully Fusion","metrics":{"Mean IoU (class)":"82.3%"},"uses_additional_data":false,"paper_date":"2019-04-03","paper":"/paper/gff-gated-fully-fusion-for-semantic","paper_url":"https://arxiv.org/abs/1904.01803v2","paper_title":"GFF: Gated Fully Fusion for Semantic Segmentation","code":"https://github.com/lxtGH/DecoupleSegNets","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":31,"model":"Auto-DeepLab-L","metrics":{"Mean IoU (class)":"82.1%"},"uses_additional_data":false,"paper_date":"2019-01-10","paper":"/paper/auto-deeplab-hierarchical-neural-architecture","paper_url":"http://arxiv.org/abs/1901.02985v2","paper_title":"Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation","code":"https://github.com/tensorflow/models","n_code_links":12,"official":{"repos":["tensorflow/models"],"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":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":1,"sample_list":"/paper/auto-deeplab-hierarchical-neural-architecture#ran","syntology_url":"https://syntology.ai/paper/1901.02985","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.02985"}}}},{"rank_in_archive_order":32,"model":"DGCNet (ResNet-101)","metrics":{"Mean IoU (class)":"82%"},"uses_additional_data":false,"paper_date":"2019-09-13","paper":"/paper/dual-graph-convolutional-network-for-semantic","paper_url":"https://arxiv.org/abs/1909.06121v3","paper_title":"Dual Graph Convolutional Network for Semantic Segmentation","code":"https://github.com/lxtGH/GALD-DGCNet","n_code_links":6,"official":null,"syntology":null},{"rank_in_archive_order":33,"model":"SPNet (ResNet-101)","metrics":{"Mean IoU (class)":"82.0%"},"uses_additional_data":false,"paper_date":"2020-03-30","paper":"/paper/2003-13328","paper_url":"https://arxiv.org/abs/2003.13328v1","paper_title":"Strip Pooling: Rethinking Spatial Pooling for Scene Parsing","code":"https://github.com/Andrew-Qibin/SPNet","n_code_links":2,"official":{"repos":["Andrew-Qibin/SPNet"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]},"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":4,"n_samples":11,"n_pointer_only_licence":3,"sample_list":"/paper/2003-13328#ran","syntology_url":"https://syntology.ai/paper/2003.13328","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.13328"}}}},{"rank_in_archive_order":34,"model":"OCR (ResNet-101)","metrics":{"Mean IoU (class)":"81.8%"},"uses_additional_data":false,"paper_date":"2019-09-24","paper":"/paper/object-contextual-representations-for","paper_url":"https://arxiv.org/abs/1909.11065v6","paper_title":"Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation","code":"https://github.com/open-mmlab/mmsegmentation","n_code_links":11,"official":{"repos":["HRNet/HRNet-Semantic-Segmentation"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":4,"n_samples":9,"n_pointer_only_licence":1,"sample_list":"/paper/object-contextual-representations-for#ran","syntology_url":"https://syntology.ai/paper/1909.11065","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11065"}}}},{"rank_in_archive_order":35,"model":"RPCNet","metrics":{"Mean IoU (class)":"81.8"},"uses_additional_data":false,"paper_date":"2020-04-16","paper":"/paper/joint-semantic-segmentation-and-boundary","paper_url":"https://arxiv.org/abs/2004.07684v1","paper_title":"Joint Semantic Segmentation and Boundary Detection using Iterative Pyramid Contexts","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":36,"model":"OCNet","metrics":{"Mean IoU (class)":"81.7%"},"uses_additional_data":false,"paper_date":"2018-09-04","paper":"/paper/ocnet-object-context-network-for-scene","paper_url":"https://arxiv.org/abs/1809.00916v4","paper_title":"OCNet: Object Context Network for Scene Parsing","code":"https://github.com/open-mmlab/mmsegmentation","n_code_links":8,"official":null,"syntology":null},{"rank_in_archive_order":37,"model":"SETR-PUP++","metrics":{"Mean IoU (class)":"81.64%"},"uses_additional_data":false,"paper_date":"2020-12-31","paper":"/paper/rethinking-semantic-segmentation-from-a","paper_url":"https://arxiv.org/abs/2012.15840v3","paper_title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","code":"https://github.com/PaddlePaddle/PaddleSeg","n_code_links":5,"official":null,"syntology":null},{"rank_in_archive_order":38,"model":"HRNet (HRNetV2-W48)","metrics":{"Mean IoU (class)":"81.6%"},"uses_additional_data":false,"paper_date":"2019-04-09","paper":"/paper/high-resolution-representations-for-labeling","paper_url":"http://arxiv.org/abs/1904.04514v1","paper_title":"High-Resolution Representations for Labeling Pixels and Regions","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":39,"official":{"repos":["leoxiaobin/deep-high-resolution-net.pytorch"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]},"syntology":{"n_ran":14,"n_constructed":0,"n_ran_checked":8,"n_instrument":6,"n_unverified":4,"n_samples":18,"n_pointer_only_licence":11,"sample_list":"/paper/high-resolution-representations-for-labeling#ran","syntology_url":"https://syntology.ai/paper/1904.04514","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.04514"}}}},{"rank_in_archive_order":39,"model":"HRNetV2 (train+val)","metrics":{"Mean IoU (class)":"81.6%"},"uses_additional_data":false,"paper_date":"2019-08-20","paper":"/paper/190807919","paper_url":"https://arxiv.org/abs/1908.07919v2","paper_title":"Deep High-Resolution Representation Learning for Visual Recognition","code":"https://github.com/open-mmlab/mmdetection","n_code_links":42,"official":null,"syntology":{"n_ran":21,"n_constructed":0,"n_ran_checked":16,"n_instrument":5,"n_unverified":13,"n_samples":34,"n_pointer_only_licence":21,"sample_list":"/paper/190807919#ran","syntology_url":"https://syntology.ai/paper/1908.07919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.07919"}}}},{"rank_in_archive_order":40,"model":"DANet (ResNet-101)","metrics":{"Mean IoU (class)":"81.5%"},"uses_additional_data":false,"paper_date":"2018-09-09","paper":"/paper/dual-attention-network-for-scene-segmentation","paper_url":"http://arxiv.org/abs/1809.02983v4","paper_title":"Dual Attention Network for Scene Segmentation","code":"https://github.com/xmu-xiaoma666/External-Attention-pytorch","n_code_links":12,"official":{"repos":["junfu1115/DANet"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_samples":7,"n_pointer_only_licence":5,"sample_list":"/paper/dual-attention-network-for-scene-segmentation#ran","syntology_url":"https://syntology.ai/paper/1809.02983","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.02983"}}}},{"rank_in_archive_order":41,"model":"CCNet","metrics":{"Mean IoU (class)":"81.4%"},"uses_additional_data":false,"paper_date":"2018-11-28","paper":"/paper/ccnet-criss-cross-attention-for-semantic","paper_url":"https://arxiv.org/abs/1811.11721v2","paper_title":"CCNet: Criss-Cross Attention for Semantic Segmentation","code":"https://github.com/open-mmlab/mmsegmentation","n_code_links":4,"official":{"repos":["speedinghzl/CCNet"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":13,"n_constructed":0,"n_ran_checked":7,"n_instrument":6,"n_unverified":1,"n_samples":14,"n_pointer_only_licence":3,"sample_list":"/paper/ccnet-criss-cross-attention-for-semantic#ran","syntology_url":"https://syntology.ai/paper/1811.11721","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.11721"}}}},{"rank_in_archive_order":42,"model":"BFP","metrics":{"Mean IoU (class)":"81.4%"},"uses_additional_data":false,"paper_date":"2019-08-31","paper":"/paper/boundary-aware-feature-propagation-for-scene","paper_url":"https://arxiv.org/abs/1909.00179v1","paper_title":"Boundary-Aware Feature Propagation for Scene Segmentation","code":"https://github.com/henghuiding/BFP","n_code_links":1,"official":{"repos":["henghuiding/BFP"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["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":1,"sample_list":"/paper/boundary-aware-feature-propagation-for-scene#ran","syntology_url":"https://syntology.ai/paper/1909.00179","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.00179"}}}},{"rank_in_archive_order":43,"model":"DeepLabv3 (ResNet-101, coarse)","metrics":{"Mean IoU (class)":"81.3%"},"uses_additional_data":false,"paper_date":"2017-06-17","paper":"/paper/rethinking-atrous-convolution-for-semantic","paper_url":"http://arxiv.org/abs/1706.05587v3","paper_title":"Rethinking Atrous Convolution for Semantic Image Segmentation","code":"https://github.com/tensorflow/models","n_code_links":77,"official":null,"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":4,"n_samples":7,"n_pointer_only_licence":3,"sample_list":"/paper/rethinking-atrous-convolution-for-semantic#ran","syntology_url":"https://syntology.ai/paper/1706.05587","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.05587"}}}},{"rank_in_archive_order":44,"model":"CPN(ResNet-101)","metrics":{"Mean IoU (class)":"81.3%"},"uses_additional_data":false,"paper_date":"2020-04-03","paper":"/paper/context-prior-for-scene-segmentation","paper_url":"https://arxiv.org/abs/2004.01547v1","paper_title":"Context Prior for Scene Segmentation","code":"https://github.com/ycszen/ContextPrior","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":45,"model":"Asymmetric ALNN","metrics":{"Mean IoU (class)":"81.3%"},"uses_additional_data":false,"paper_date":"2019-08-21","paper":"/paper/asymmetric-non-local-neural-networks-for","paper_url":"https://arxiv.org/abs/1908.07678v5","paper_title":"Asymmetric Non-local Neural Networks for Semantic Segmentation","code":"https://github.com/open-mmlab/mmsegmentation","n_code_links":5,"official":{"repos":["MendelXu/ANN","donnyyou/torchcv"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["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":0,"sample_list":"/paper/asymmetric-non-local-neural-networks-for#ran","syntology_url":"https://syntology.ai/paper/1908.07678","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.07678"}}}},{"rank_in_archive_order":46,"model":"AdapNet++","metrics":{"Mean IoU (class)":"81.24%"},"uses_additional_data":false,"paper_date":"2018-08-11","paper":"/paper/self-supervised-model-adaptation-for","paper_url":"https://arxiv.org/abs/1808.03833v3","paper_title":"Self-Supervised Model Adaptation for Multimodal Semantic Segmentation","code":"https://github.com/DeepSceneSeg/SSMA","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":47,"model":"SVCNet (ResNet-101)","metrics":{"Mean IoU (class)":"81.0%"},"uses_additional_data":false,"paper_date":"2019-09-05","paper":"/paper/semantic-correlation-promoted-shape-variant-1","paper_url":"https://arxiv.org/abs/1909.02651v1","paper_title":"Semantic Correlation Promoted Shape-Variant Context for Segmentation","code":"https://github.com/henghuiding/SVC","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":48,"model":"D3Net-L","metrics":{"Mean IoU (class)":"80.8%"},"uses_additional_data":false,"paper_date":"2020-11-21","paper":"/paper/densely-connected-multidilated-convolutional","paper_url":"https://arxiv.org/abs/2011.11844v2","paper_title":"Densely connected multidilated convolutional networks for dense prediction tasks","code":"https://github.com/sony/ai-research-code","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":49,"model":"DenseASPP (DenseNet-161)","metrics":{"Mean IoU (class)":"80.6%"},"uses_additional_data":false,"paper_date":"2018-06-01","paper":"/paper/denseaspp-for-semantic-segmentation-in-street","paper_url":"http://openaccess.thecvf.com/content_cvpr_2018/html/Yang_DenseASPP_for_Semantic_CVPR_2018_paper.html","paper_title":"DenseASPP for Semantic Segmentation in Street Scenes","code":"https://github.com/DeepMotionAIResearch/DenseASPP","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":50,"model":"Smooth Network with Channel Attention Block","metrics":{"Mean IoU (class)":"80.3%"},"uses_additional_data":false,"paper_date":"2018-04-25","paper":"/paper/learning-a-discriminative-feature-network-for","paper_url":"http://arxiv.org/abs/1804.09337v1","paper_title":"Learning a Discriminative Feature Network for Semantic Segmentation","code":"https://github.com/ycszen/TorchSeg","n_code_links":3,"official":null,"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":5,"n_samples":8,"n_pointer_only_licence":0,"sample_list":"/paper/learning-a-discriminative-feature-network-for#ran","syntology_url":"https://syntology.ai/paper/1804.09337","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.09337"}}}},{"rank_in_archive_order":51,"model":"PSPNet++","metrics":{"Mean IoU (class)":"80.2%"},"uses_additional_data":false,"paper_date":"2016-12-04","paper":"/paper/pyramid-scene-parsing-network","paper_url":"http://arxiv.org/abs/1612.01105v2","paper_title":"Pyramid Scene Parsing Network","code":"https://github.com/tensorflow/models","n_code_links":67,"official":{"repos":["hszhao/PSPNet"],"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":21,"n_constructed":0,"n_ran_checked":14,"n_instrument":7,"n_unverified":8,"n_samples":29,"n_pointer_only_licence":5,"sample_list":"/paper/pyramid-scene-parsing-network#ran","syntology_url":"https://syntology.ai/paper/1612.01105","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1612.01105"}}}},{"rank_in_archive_order":52,"model":"PSANet (ResNet-101)","metrics":{"Mean IoU (class)":"80.1%"},"uses_additional_data":false,"paper_date":"2018-09-01","paper":"/paper/psanet-point-wise-spatial-attention-network","paper_url":"http://openaccess.thecvf.com/content_ECCV_2018/html/Hengshuang_Zhao_PSANet_Point-wise_Spatial_ECCV_2018_paper.html","paper_title":"PSANet: Point-wise Spatial Attention Network for Scene Parsing","code":"https://github.com/open-mmlab/mmsegmentation","n_code_links":4,"official":null,"syntology":null},{"rank_in_archive_order":53,"model":"ESANet-R34-NBt1D","metrics":{"Mean IoU (class)":"80.09%"},"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":54,"model":"DeepLabV3 with R-101","metrics":{"Mean IoU (class)":"79.9%"},"uses_additional_data":false,"paper_date":"2023-07-26","paper":"/paper/resolution-aware-design-of-atrous-rates-for","paper_url":"https://arxiv.org/abs/2307.14179v1","paper_title":"Resolution-Aware Design of Atrous Rates for Semantic Segmentation Networks","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":55,"model":"DFN (ResNet-101)","metrics":{"Mean IoU (class)":"79.3%"},"uses_additional_data":false,"paper_date":"2018-04-25","paper":"/paper/learning-a-discriminative-feature-network-for","paper_url":"http://arxiv.org/abs/1804.09337v1","paper_title":"Learning a Discriminative Feature Network for Semantic Segmentation","code":"https://github.com/ycszen/TorchSeg","n_code_links":3,"official":null,"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":5,"n_samples":8,"n_pointer_only_licence":0,"sample_list":"/paper/learning-a-discriminative-feature-network-for#ran","syntology_url":"https://syntology.ai/paper/1804.09337","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.09337"}}}},{"rank_in_archive_order":56,"model":"AAF (ResNet-101)","metrics":{"Mean IoU (class)":"79.1%"},"uses_additional_data":false,"paper_date":"2018-03-27","paper":"/paper/adaptive-affinity-fields-for-semantic","paper_url":"http://arxiv.org/abs/1803.10335v3","paper_title":"Adaptive Affinity Fields for Semantic Segmentation","code":"https://github.com/twke18/Adaptive_Affinity_Fields","n_code_links":1,"official":null,"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1,"sample_list":"/paper/adaptive-affinity-fields-for-semantic#ran","syntology_url":"https://syntology.ai/paper/1803.10335","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.10335"}}}},{"rank_in_archive_order":57,"model":"ShelfNet-34","metrics":{"Mean IoU (class)":"79.0%"},"uses_additional_data":false,"paper_date":"2018-11-27","paper":"/paper/multi-path-segmentation-network","paper_url":"https://arxiv.org/abs/1811.11254v6","paper_title":"ShelfNet for Fast Semantic Segmentation","code":"https://github.com/Deci-AI/super-gradients","n_code_links":6,"official":null,"syntology":null},{"rank_in_archive_order":58,"model":"BiSeNet (ResNet-101)","metrics":{"Mean IoU (class)":"78.9%"},"uses_additional_data":false,"paper_date":"2018-08-02","paper":"/paper/bisenet-bilateral-segmentation-network-for","paper_url":"http://arxiv.org/abs/1808.00897v1","paper_title":"BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation","code":"https://github.com/PaddlePaddle/PaddleSeg","n_code_links":21,"official":null,"syntology":{"n_ran":14,"n_constructed":0,"n_ran_checked":9,"n_instrument":5,"n_unverified":4,"n_samples":18,"n_pointer_only_licence":3,"sample_list":"/paper/bisenet-bilateral-segmentation-network-for#ran","syntology_url":"https://syntology.ai/paper/1808.00897","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.00897"}}}},{"rank_in_archive_order":59,"model":"ResNet-38","metrics":{"Mean IoU (class)":"78.4%"},"uses_additional_data":false,"paper_date":"2016-11-30","paper":"/paper/wider-or-deeper-revisiting-the-resnet-model","paper_url":"http://arxiv.org/abs/1611.10080v1","paper_title":"Wider or Deeper: Revisiting the ResNet Model for Visual Recognition","code":"https://github.com/itijyou/ademxapp","n_code_links":3,"official":{"repos":["itijyou/ademxapp"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":2,"sample_list":"/paper/wider-or-deeper-revisiting-the-resnet-model#ran","syntology_url":"https://syntology.ai/paper/1611.10080","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.10080"}}}},{"rank_in_archive_order":60,"model":"PSPNet","metrics":{"Mean IoU (class)":"78.4%"},"uses_additional_data":false,"paper_date":"2016-12-04","paper":"/paper/pyramid-scene-parsing-network","paper_url":"http://arxiv.org/abs/1612.01105v2","paper_title":"Pyramid Scene Parsing Network","code":"https://github.com/tensorflow/models","n_code_links":67,"official":{"repos":["hszhao/PSPNet"],"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":21,"n_constructed":0,"n_ran_checked":14,"n_instrument":7,"n_unverified":8,"n_samples":29,"n_pointer_only_licence":5,"sample_list":"/paper/pyramid-scene-parsing-network#ran","syntology_url":"https://syntology.ai/paper/1612.01105","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1612.01105"}}}},{"rank_in_archive_order":61,"model":"DepthSeg (ResNet-101)","metrics":{"Mean IoU (class)":"78.2%"},"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":62,"model":"DSSPN (ResNet-101)","metrics":{"Mean IoU (class)":"77.8%"},"uses_additional_data":false,"paper_date":"2018-03-16","paper":"/paper/dynamic-structured-semantic-propagation","paper_url":"http://arxiv.org/abs/1803.06067v1","paper_title":"Dynamic-structured Semantic Propagation Network","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":63,"model":"DUC-HDC (ResNet-101)","metrics":{"Mean IoU (class)":"77.6%"},"uses_additional_data":false,"paper_date":"2017-02-27","paper":"/paper/understanding-convolution-for-semantic","paper_url":"http://arxiv.org/abs/1702.08502v3","paper_title":"Understanding Convolution for Semantic Segmentation","code":"https://github.com/y-ouali/pytorch_segmentation","n_code_links":5,"official":{"repos":["TuSimple/TuSimple-DUC"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1,"sample_list":"/paper/understanding-convolution-for-semantic#ran","syntology_url":"https://syntology.ai/paper/1702.08502","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1702.08502"}}}},{"rank_in_archive_order":64,"model":"SaGe","metrics":{"Mean IoU (class)":"76.9"},"uses_additional_data":false,"paper_date":"2021-11-25","paper":"/paper/semantic-aware-generation-for-self-supervised","paper_url":"https://arxiv.org/abs/2111.13163v1","paper_title":"Semantic-Aware Generation for Self-Supervised Visual Representation Learning","code":"https://github.com/sunsmarterjie/sage","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":65,"model":"SwinMTL","metrics":{"Mean IoU (class)":"76.41%"},"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":66,"model":"SwiftNetRN-18","metrics":{"Mean IoU (class)":"75.5%"},"uses_additional_data":false,"paper_date":"2019-03-20","paper":"/paper/in-defense-of-pre-trained-imagenet","paper_url":"http://arxiv.org/abs/1903.08469v2","paper_title":"In Defense of Pre-trained ImageNet Architectures for Real-time Semantic Segmentation of Road-driving Images","code":"https://github.com/XuJiacong/PIDNet","n_code_links":6,"official":null,"syntology":null},{"rank_in_archive_order":67,"model":"RefineNet (ResNet-101)","metrics":{"Mean IoU (class)":"73.6%"},"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":68,"model":"MobileNet V3-Large 1.0","metrics":{"Mean IoU (class)":"72.6%"},"uses_additional_data":false,"paper_date":"2019-05-06","paper":"/paper/searching-for-mobilenetv3","paper_url":"https://arxiv.org/abs/1905.02244v5","paper_title":"Searching for MobileNetV3","code":"https://github.com/tensorflow/models","n_code_links":67,"official":null,"syntology":{"n_ran":86,"n_constructed":22,"n_ran_checked":75,"n_instrument":11,"n_unverified":19,"n_samples":105,"n_pointer_only_licence":46,"sample_list":"/paper/searching-for-mobilenetv3#ran","syntology_url":"https://syntology.ai/paper/1905.02244","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.02244"}}}},{"rank_in_archive_order":69,"model":"SqueezeNAS (LAT Large)","metrics":{"Mean IoU (class)":"72.5%"},"uses_additional_data":false,"paper_date":"2019-08-05","paper":"/paper/squeezenas-fast-neural-architecture-search","paper_url":"https://arxiv.org/abs/1908.01748v2","paper_title":"SqueezeNAS: Fast neural architecture search for faster semantic segmentation","code":"https://github.com/ashaw596/squeezenas","n_code_links":1,"official":null,"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":0,"sample_list":"/paper/squeezenas-fast-neural-architecture-search#ran","syntology_url":"https://syntology.ai/paper/1908.01748","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.01748"}}}},{"rank_in_archive_order":70,"model":"Multi Scale Spatial Attention","metrics":{"Mean IoU (class)":"72.4%"},"uses_additional_data":false,"paper_date":"2020-06-30","paper":"/paper/semantic-segmentation-with-multi-scale","paper_url":"https://arxiv.org/abs/2007.12685v3","paper_title":"Semantic Segmentation With Multi Scale Spatial Attention For Self Driving Cars","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":71,"model":"FRRN","metrics":{"Mean IoU (class)":"71.8%"},"uses_additional_data":false,"paper_date":"2016-11-24","paper":"/paper/full-resolution-residual-networks-for","paper_url":"http://arxiv.org/abs/1611.08323v2","paper_title":"Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes","code":"https://github.com/TobyPDE/FRRN","n_code_links":4,"official":{"repos":["TobyPDE/FRRN"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3,"sample_list":"/paper/full-resolution-residual-networks-for#ran","syntology_url":"https://syntology.ai/paper/1611.08323","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.08323"}}}},{"rank_in_archive_order":72,"model":"LRR-4x","metrics":{"Mean IoU (class)":"71.8%"},"uses_additional_data":false,"paper_date":"2016-05-08","paper":"/paper/laplacian-pyramid-reconstruction-and","paper_url":"http://arxiv.org/abs/1605.02264v2","paper_title":"Laplacian Pyramid Reconstruction and Refinement for Semantic Segmentation","code":"https://github.com/golnazghiasi/LRR","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":73,"model":"Context","metrics":{"Mean IoU (class)":"71.6%"},"uses_additional_data":false,"paper_date":"2015-04-04","paper":"/paper/efficient-piecewise-training-of-deep","paper_url":"http://arxiv.org/abs/1504.01013v4","paper_title":"Efficient piecewise training of deep structured models for semantic segmentation","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":74,"model":"FasterSeg","metrics":{"Mean IoU (class)":"71.5%"},"uses_additional_data":false,"paper_date":"2019-12-23","paper":"/paper/fasterseg-searching-for-faster-real-time-1","paper_url":"https://arxiv.org/abs/1912.10917v2","paper_title":"FasterSeg: Searching for Faster Real-time Semantic Segmentation","code":"https://github.com/TAMU-VITA/FasterSeg","n_code_links":2,"official":{"repos":["TAMU-VITA/FasterSeg"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":2,"n_samples":13,"n_pointer_only_licence":2,"sample_list":"/paper/fasterseg-searching-for-faster-real-time-1#ran","syntology_url":"https://syntology.ai/paper/1912.10917","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.10917"}}}},{"rank_in_archive_order":75,"model":"DFANet A","metrics":{"Mean IoU (class)":"71.3%"},"uses_additional_data":false,"paper_date":"2019-04-03","paper":"/paper/dfanet-deep-feature-aggregation-for-real-time","paper_url":"http://arxiv.org/abs/1904.02216v1","paper_title":"DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation","code":"https://github.com/huaifeng1993/DFANet","n_code_links":2,"official":null,"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1,"sample_list":"/paper/dfanet-deep-feature-aggregation-for-real-time#ran","syntology_url":"https://syntology.ai/paper/1904.02216","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.02216"}}}},{"rank_in_archive_order":76,"model":"LDFNet","metrics":{"Mean IoU (class)":"71.3"},"uses_additional_data":false,"paper_date":"2018-09-24","paper":"/paper/incorporating-luminance-depth-and-color","paper_url":"https://arxiv.org/abs/1809.09077v3","paper_title":"Incorporating Luminance, Depth and Color Information by a Fusion-based Network for Semantic Segmentation","code":"https://github.com/shangweihung/LDFNet","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":77,"model":"LightSeg-DarkNet19","metrics":{"Category mIoU":"88.29","Mean IoU (class)":"70.75%"},"uses_additional_data":false,"paper_date":"2019-12-13","paper":"/paper/liteseg-a-novel-lightweight-convnet-for","paper_url":"https://arxiv.org/abs/1912.06683v1","paper_title":"LiteSeg: A Novel Lightweight ConvNet for Semantic Segmentation","code":"https://github.com/zh320/realtime-semantic-segmentation-pytorch","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":78,"model":"ESNet","metrics":{"Mean IoU (class)":"70.7%"},"uses_additional_data":false,"paper_date":"2019-06-24","paper":"/paper/esnet-an-efficient-symmetric-network-for-real","paper_url":"https://arxiv.org/abs/1906.09826v1","paper_title":"ESNet: An Efficient Symmetric Network for Real-time Semantic Segmentation","code":"https://github.com/osmr/imgclsmob","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":79,"model":"ICNet","metrics":{"Mean IoU (class)":"70.6%"},"uses_additional_data":false,"paper_date":"2017-04-27","paper":"/paper/icnet-for-real-time-semantic-segmentation-on","paper_url":"http://arxiv.org/abs/1704.08545v2","paper_title":"ICNet for Real-Time Semantic Segmentation on High-Resolution Images","code":"https://github.com/osmr/imgclsmob","n_code_links":18,"official":null,"syntology":null},{"rank_in_archive_order":80,"model":"LEDNet","metrics":{"Mean IoU (class)":"70.6%"},"uses_additional_data":false,"paper_date":"2019-05-07","paper":"/paper/lednet-a-lightweight-encoder-decoder-network","paper_url":"https://arxiv.org/abs/1905.02423v3","paper_title":"LEDNet: A Lightweight Encoder-Decoder Network for Real-Time Semantic Segmentation","code":"https://github.com/osmr/imgclsmob","n_code_links":6,"official":null,"syntology":null},{"rank_in_archive_order":81,"model":"WASPnet (ours)","metrics":{"Mean IoU (class)":"70.5%"},"uses_additional_data":false,"paper_date":"2019-12-06","paper":"/paper/waterfall-atrous-spatial-pooling-architecture","paper_url":"https://arxiv.org/abs/1912.03183v1","paper_title":"Waterfall Atrous Spatial Pooling Architecture for Efficient Semantic Segmentation","code":"https://github.com/bmartacho/WASP","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":82,"model":"DeepLab-CRF (ResNet-101)","metrics":{"Mean IoU (class)":"70.4%"},"uses_additional_data":false,"paper_date":"2016-06-02","paper":"/paper/deeplab-semantic-image-segmentation-with-deep","paper_url":"http://arxiv.org/abs/1606.00915v2","paper_title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","code":"https://github.com/tensorflow/models/tree/master/research/deeplab","n_code_links":47,"official":null,"syntology":{"n_ran":43,"n_constructed":12,"n_ran_checked":35,"n_instrument":8,"n_unverified":20,"n_samples":63,"n_pointer_only_licence":18,"sample_list":"/paper/deeplab-semantic-image-segmentation-with-deep#ran","syntology_url":"https://syntology.ai/paper/1606.00915","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.00915"}}}},{"rank_in_archive_order":83,"model":"ERFNet (PyTorch)","metrics":{"Mean IoU (class)":"69.8%"},"uses_additional_data":false,"paper_date":"2017-10-09","paper":"/paper/erfnet-efficient-residual-factorized-convnet","paper_url":"https://ieeexplore.ieee.org/abstract/document/8063438","paper_title":"ERFNet: Efficient Residual Factorized ConvNet for Real-time Semantic Segmentation","code":"https://github.com/osmr/imgclsmob","n_code_links":13,"official":null,"syntology":null},{"rank_in_archive_order":84,"model":"Fast-SCNN","metrics":{"Mean IoU (class)":"68%"},"uses_additional_data":false,"paper_date":"2019-02-12","paper":"/paper/fast-scnn-fast-semantic-segmentation-network","paper_url":"http://arxiv.org/abs/1902.04502v1","paper_title":"Fast-SCNN: Fast Semantic Segmentation Network","code":"https://github.com/open-mmlab/mmsegmentation","n_code_links":24,"official":null,"syntology":{"n_ran":21,"n_constructed":0,"n_ran_checked":21,"n_instrument":0,"n_unverified":11,"n_samples":32,"n_pointer_only_licence":0,"sample_list":"/paper/fast-scnn-fast-semantic-segmentation-network#ran","syntology_url":"https://syntology.ai/paper/1902.04502","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.04502"}}}},{"rank_in_archive_order":85,"model":"LightSeg-MobileNet","metrics":{"Category mIoU":"86.79","Mean IoU (class)":"67.81%"},"uses_additional_data":false,"paper_date":"2019-12-13","paper":"/paper/liteseg-a-novel-lightweight-convnet-for","paper_url":"https://arxiv.org/abs/1912.06683v1","paper_title":"LiteSeg: A Novel Lightweight ConvNet for Semantic Segmentation","code":"https://github.com/zh320/realtime-semantic-segmentation-pytorch","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":86,"model":"LiteSeg-MobileNet","metrics":{"Mean IoU (class)":"67.81%"},"uses_additional_data":false,"paper_date":"2019-12-13","paper":"/paper/liteseg-a-novel-lightweight-convnet-for","paper_url":"https://arxiv.org/abs/1912.06683v1","paper_title":"LiteSeg: A Novel Lightweight ConvNet for Semantic Segmentation","code":"https://github.com/zh320/realtime-semantic-segmentation-pytorch","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":87,"model":"Template-Based NAS-arch1","metrics":{"Mean IoU (class)":"67.8%"},"uses_additional_data":false,"paper_date":"2019-04-04","paper":"/paper/template-based-automatic-search-of-compact","paper_url":"https://arxiv.org/abs/1904.02365v2","paper_title":"Template-Based Automatic Search of Compact Semantic Segmentation Architectures","code":"https://github.com/drsleep/nas-segm-pytorch","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":88,"model":"Template-Based NAS-arch0","metrics":{"Mean IoU (class)":"67.7%"},"uses_additional_data":false,"paper_date":"2019-04-04","paper":"/paper/template-based-automatic-search-of-compact","paper_url":"https://arxiv.org/abs/1904.02365v2","paper_title":"Template-Based Automatic Search of Compact Semantic Segmentation Architectures","code":"https://github.com/drsleep/nas-segm-pytorch","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":89,"model":"EDANet","metrics":{"Mean IoU (class)":"67.3"},"uses_additional_data":false,"paper_date":"2018-09-17","paper":"/paper/efficient-dense-modules-of-asymmetric","paper_url":"https://arxiv.org/abs/1809.06323v3","paper_title":"Efficient Dense Modules of Asymmetric Convolution for Real-Time Semantic Segmentation","code":"https://github.com/osmr/imgclsmob","n_code_links":4,"official":null,"syntology":null},{"rank_in_archive_order":90,"model":"Dilation10","metrics":{"Mean IoU (class)":"67.1%"},"uses_additional_data":false,"paper_date":"2015-11-23","paper":"/paper/multi-scale-context-aggregation-by-dilated","paper_url":"http://arxiv.org/abs/1511.07122v3","paper_title":"Multi-Scale Context Aggregation by Dilated Convolutions","code":"https://github.com/fyu/dilation","n_code_links":9,"official":{"repos":["fyu/dilation"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":2,"n_samples":8,"n_pointer_only_licence":2,"sample_list":"/paper/multi-scale-context-aggregation-by-dilated#ran","syntology_url":"https://syntology.ai/paper/1511.07122","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1511.07122"}}}},{"rank_in_archive_order":91,"model":"DPN","metrics":{"Mean IoU (class)":"66.8%"},"uses_additional_data":false,"paper_date":"2015-09-09","paper":"/paper/semantic-image-segmentation-via-deep-parsing","paper_url":"http://arxiv.org/abs/1509.02634v2","paper_title":"Semantic Image Segmentation via Deep Parsing Network","code":"https://github.com/luwill/Semantic-Segmentation-Guide","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":92,"model":"SqueezeNAS (LAT Small)","metrics":{"Mean IoU (class)":"66.8%"},"uses_additional_data":false,"paper_date":"2019-08-05","paper":"/paper/squeezenas-fast-neural-architecture-search","paper_url":"https://arxiv.org/abs/1908.01748v2","paper_title":"SqueezeNAS: Fast neural architecture search for faster semantic segmentation","code":"https://github.com/ashaw596/squeezenas","n_code_links":1,"official":null,"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":0,"sample_list":"/paper/squeezenas-fast-neural-architecture-search#ran","syntology_url":"https://syntology.ai/paper/1908.01748","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.01748"}}}},{"rank_in_archive_order":93,"model":"SINet","metrics":{"Mean IoU (class)":"66.5%"},"uses_additional_data":false,"paper_date":"2019-11-20","paper":"/paper/sinet-extreme-lightweight-portrait","paper_url":"https://arxiv.org/abs/1911.09099v4","paper_title":"SINet: Extreme Lightweight Portrait Segmentation Networks with Spatial Squeeze Modules and Information Blocking Decoder","code":"https://github.com/royshil/obs-backgroundremoval","n_code_links":8,"official":null,"syntology":null},{"rank_in_archive_order":94,"model":"ESPNetv2","metrics":{"Mean IoU (class)":"66.2%"},"uses_additional_data":false,"paper_date":"2018-11-28","paper":"/paper/espnetv2-a-light-weight-power-efficient-and","paper_url":"http://arxiv.org/abs/1811.11431v3","paper_title":"ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network","code":"https://github.com/PaddlePaddle/PaddleSeg","n_code_links":10,"official":{"repos":["sacmehta/EdgeNets"],"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":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":0,"sample_list":"/paper/espnetv2-a-light-weight-power-efficient-and#ran","syntology_url":"https://syntology.ai/paper/1811.11431","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.11431"}}}},{"rank_in_archive_order":95,"model":"FCN","metrics":{"Mean IoU (class)":"65.3%"},"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},{"rank_in_archive_order":96,"model":"LightSeg-ShuffleNet","metrics":{"Category mIoU":"85.39","Mean IoU (class)":"65.17%"},"uses_additional_data":false,"paper_date":"2019-12-13","paper":"/paper/liteseg-a-novel-lightweight-convnet-for","paper_url":"https://arxiv.org/abs/1912.06683v1","paper_title":"LiteSeg: A Novel Lightweight ConvNet for Semantic Segmentation","code":"https://github.com/zh320/realtime-semantic-segmentation-pytorch","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":97,"model":"LiteSeg-ShuffleNet","metrics":{"Mean IoU (class)":"65.17%"},"uses_additional_data":false,"paper_date":"2019-12-13","paper":"/paper/liteseg-a-novel-lightweight-convnet-for","paper_url":"https://arxiv.org/abs/1912.06683v1","paper_title":"LiteSeg: A Novel Lightweight ConvNet for Semantic Segmentation","code":"https://github.com/zh320/realtime-semantic-segmentation-pytorch","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":98,"model":"DeepLab","metrics":{"Mean IoU (class)":"63.1%"},"uses_additional_data":false,"paper_date":"2014-12-22","paper":"/paper/semantic-image-segmentation-with-deep","paper_url":"http://arxiv.org/abs/1412.7062v4","paper_title":"Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs","code":"https://github.com/tensorflow/models","n_code_links":18,"official":{"repos":["bitbucket.org/deeplab/deeplab-public"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"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":1,"sample_list":"/paper/semantic-image-segmentation-with-deep#ran","syntology_url":"https://syntology.ai/paper/1412.7062","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1412.7062"}}}},{"rank_in_archive_order":99,"model":"ENet + Lovász-Softmax","metrics":{"Mean IoU (class)":"63.06%"},"uses_additional_data":false,"paper_date":"2017-05-24","paper":"/paper/the-lovasz-softmax-loss-a-tractable-surrogate","paper_url":"http://arxiv.org/abs/1705.08790v2","paper_title":"The Lovász-Softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks","code":"https://github.com/CoinCheung/pytorch-loss","n_code_links":4,"official":null,"syntology":null},{"rank_in_archive_order":100,"model":"ESPNet","metrics":{"Mean IoU (class)":"60.3%"},"uses_additional_data":false,"paper_date":"2018-03-19","paper":"/paper/espnet-efficient-spatial-pyramid-of-dilated","paper_url":"http://arxiv.org/abs/1803.06815v3","paper_title":"ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation","code":"https://github.com/PaddlePaddle/PaddleSeg","n_code_links":8,"official":{"repos":["sacmehta/ESPNet"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":1,"n_samples":10,"n_pointer_only_licence":0,"sample_list":"/paper/espnet-efficient-spatial-pyramid-of-dilated#ran","syntology_url":"https://syntology.ai/paper/1803.06815","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.06815"}}}},{"rank_in_archive_order":101,"model":"ENet","metrics":{"Mean IoU (class)":"58.3%"},"uses_additional_data":false,"paper_date":"2016-06-07","paper":"/paper/enet-a-deep-neural-network-architecture-for","paper_url":"http://arxiv.org/abs/1606.02147v1","paper_title":"ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation","code":"https://github.com/PaddlePaddle/PaddleSeg","n_code_links":49,"official":null,"syntology":{"n_ran":26,"n_constructed":0,"n_ran_checked":22,"n_instrument":4,"n_unverified":4,"n_samples":30,"n_pointer_only_licence":2,"sample_list":"/paper/enet-a-deep-neural-network-architecture-for#ran","syntology_url":"https://syntology.ai/paper/1606.02147","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.02147"}}}},{"rank_in_archive_order":102,"model":"SegNet","metrics":{"Mean IoU (class)":"57.0%"},"uses_additional_data":false,"paper_date":"2015-11-02","paper":"/paper/segnet-a-deep-convolutional-encoder-decoder","paper_url":"http://arxiv.org/abs/1511.00561v3","paper_title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","code":"https://github.com/PaddlePaddle/PaddleSeg","n_code_links":74,"official":null,"syntology":{"n_ran":22,"n_constructed":0,"n_ran_checked":14,"n_instrument":8,"n_unverified":22,"n_samples":44,"n_pointer_only_licence":11,"sample_list":"/paper/segnet-a-deep-convolutional-encoder-decoder#ran","syntology_url":"https://syntology.ai/paper/1511.00561","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1511.00561"}}}},{"rank_in_archive_order":103,"model":"IkshanaNet-1","metrics":{"Category mIoU":"82.22%","Mean IoU (class)":"54.82%"},"uses_additional_data":false,"paper_date":"2021-01-21","paper":"/paper/ikshana-a-theory-of-human-scene-understanding","paper_url":"https://arxiv.org/abs/2101.10837v4","paper_title":"The Ikshana Hypothesis of Human Scene Understanding","code":"https://github.com/dvssajay/The-Ikshana-Hypothesis-of-Human-Scene-Understanding-Mechanism","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":104,"model":"IkshanaNet-2","metrics":{"Category mIoU":"76.73%","Mean IoU (class)":"45.02%"},"uses_additional_data":false,"paper_date":"2021-01-21","paper":"/paper/ikshana-a-theory-of-human-scene-understanding","paper_url":"https://arxiv.org/abs/2101.10837v4","paper_title":"The Ikshana Hypothesis of Human Scene Understanding","code":"https://github.com/dvssajay/The-Ikshana-Hypothesis-of-Human-Scene-Understanding-Mechanism","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":105,"model":"IkshanaNet-3","metrics":{"Category mIoU":"75.61%","Mean IoU (class)":"42.07%"},"uses_additional_data":false,"paper_date":"2021-01-21","paper":"/paper/ikshana-a-theory-of-human-scene-understanding","paper_url":"https://arxiv.org/abs/2101.10837v4","paper_title":"The Ikshana Hypothesis of Human Scene Understanding","code":"https://github.com/dvssajay/The-Ikshana-Hypothesis-of-Human-Scene-Understanding-Mechanism","n_code_links":2,"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), 1 had this board among the leaderboards the extractor considered for their tables (it keeps at most 10 boards per paper and 4 per dataset; the lists of 1,595 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), and none proposed a result, so none await a verdict and none were placed.","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":105,"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":1595,"candidates":1,"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":47,"rows_with_any_sample_ran":45,"rows_with_a_run_with_no_instrument_failure":41,"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":32,"rows_whose_official_repository_has_a_sample_that_ran":19,"rows_whose_official_repository_has_a_run_with_no_instrument_failure":12,"rows_community_repositories_only":5,"rows_runs_from_other_or_unrecorded_repositories":2,"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":40,"distinct_papers_with_any_sample_ran":38,"distinct_papers_with_a_run_with_no_instrument_failure":34,"samples_over_distinct_papers":{"n_ran":487,"n_constructed":57,"n_ran_checked":374,"n_instrument":113,"n_unverified":195,"n_samples":682,"n_pointer_only_licence":203,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":536,"n_constructed":57,"n_ran_checked":400,"n_instrument":136,"n_unverified":224,"n_samples":760,"n_pointer_only_licence":212,"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":"cb113a678c5b15a2c244b267edbbf3ef6acce9e372f1fb4a07fca248ad2b3e4e","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}