{"url":"/sota/medical-image-segmentation-on-kvasir-seg","task":{"name":"Medical Image Segmentation","url":"/task/medical-image-segmentation","note":null},"dataset":{"name":"Kvasir-SEG","url":"/dataset/kvasir-seg"},"category":"Computer Vision","categories":["Computer Vision","Medical"],"category_note":null,"description":"**Medical Image Segmentation** is a computer vision task that involves dividing an medical image into multiple segments, where each segment represents a different object or structure of interest in the image. The goal of medical image segmentation is to provide a precise and accurate representation of the objects of interest within the image, typically for the purpose of diagnosis, treatment planning, and quantitative analysis.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [IVD-Net](https://github.com/josedolz/IVD-Net) )</span>","description_from":"task","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 Dice","Average MAE","S-Measure","max E-Measure","mIoU","FPS","F-measure","Precision","Recall"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"mean Dice":"higher","Average MAE":"lower","S-Measure":null,"max E-Measure":null,"mIoU":null,"FPS":null,"F-measure":null,"Precision":"higher","Recall":"higher"}},"counts":{"rows":58,"rows_with_code":49,"rows_with_paper_page":58,"rows_dated":58,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"DUCK-Net","metrics":{"Precision":"0.9628","Recall":"0.9379","mIoU":"0.9051","mean Dice":"0.9502"},"uses_additional_data":false,"paper_date":"2023-11-03","paper":"/paper/using-duck-net-for-polyp-image-segmentation-1","paper_url":"https://arxiv.org/abs/2311.02239v1","paper_title":"Using DUCK-Net for Polyp Image Segmentation","code":"https://github.com/RazvanDu/DUCK-Net","n_code_links":2,"syntology":null},{"rank_in_archive_order":2,"model":"EffiSegNet-B5","metrics":{"F-measure":"0.9513","Precision":"0.9713","Recall":"0.9321","mIoU":"0.9065","mean Dice":"0.9488"},"uses_additional_data":false,"paper_date":"2024-07-23","paper":"/paper/effisegnet-gastrointestinal-polyp","paper_url":"https://arxiv.org/abs/2407.16298v1","paper_title":"EffiSegNet: Gastrointestinal Polyp Segmentation through a Pre-Trained EfficientNet-based Network with a Simplified Decoder","code":"https://github.com/ivezakis/effisegnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"EffiSegNet-B4","metrics":{"F-measure":"0.9552","Precision":"0.9679","Recall":"0.9429","mIoU":"0.9056","mean Dice":"0.9483"},"uses_additional_data":false,"paper_date":"2024-07-23","paper":"/paper/effisegnet-gastrointestinal-polyp","paper_url":"https://arxiv.org/abs/2407.16298v1","paper_title":"EffiSegNet: Gastrointestinal Polyp Segmentation through a Pre-Trained EfficientNet-based Network with a Simplified Decoder","code":"https://github.com/ivezakis/effisegnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"SegMed","metrics":{"mIoU":"0.899","mean Dice":"0.947"},"uses_additional_data":false,"paper_date":"2025-01-31","paper":"/paper/from-semantic-segmentation-of-natural-images","paper_url":"https://link.springer.com/chapter/10.1007/978-3-031-80507-3_12","paper_title":"From Semantic Segmentation of Natural Images to Medical Image Segmentation Using ViT-Based Architectures","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":5,"model":"FCB Former","metrics":{"mIoU":"0.8974","mean Dice":"0.9445"},"uses_additional_data":false,"paper_date":"2022-07-16","paper":"/paper/adaptive-t-vmf-dice-loss-for-multi-class","paper_url":"https://arxiv.org/abs/2207.07842v1","paper_title":"Adaptive t-vMF Dice Loss for Multi-class Medical Image Segmentation","code":"https://github.com/usagisukisuki/adaptive_t-vmf_dice_loss","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"FCB-SwinV2 Transformer","metrics":{"mIoU":"0.8973","mean Dice":"0.9420"},"uses_additional_data":false,"paper_date":"2023-02-02","paper":"/paper/fcb-swinv2-transformer-for-polyp-segmentation","paper_url":"https://arxiv.org/abs/2302.01027v1","paper_title":"FCB-SwinV2 Transformer for Polyp Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"SEP","metrics":{"mIoU":"0.9002","mean Dice":"0.9411"},"uses_additional_data":false,"paper_date":"2022-11-15","paper":"/paper/spatially-exclusive-pasting-a-general-data","paper_url":"https://arxiv.org/abs/2211.08284v3","paper_title":"Spatially Exclusive Pasting: A General Data Augmentation for the Polyp Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":8,"model":"LM-Net","metrics":{"Precision":"0.8964","Recall":"0.9038","mIoU":"0.8912","mean Dice":"0.9409"},"uses_additional_data":false,"paper_date":"2025-01-07","paper":"/paper/lm-net-a-light-weight-and-multi-scale-network","paper_url":"https://arxiv.org/abs/2501.03838v1","paper_title":"LM-Net: A Light-weight and Multi-scale Network for Medical Image Segmentation","code":"https://github.com/Asunatan/LM-Net","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"RAPUNet","metrics":{"mIoU":"0.885","mean Dice":"0.939"},"uses_additional_data":false,"paper_date":"2024-09-16","paper":"/paper/metaformer-and-cnn-hybrid-model-for-polyp","paper_url":"https://ieeexplore.ieee.org/document/10681057","paper_title":"MetaFormer and CNN Hybrid Model for Polyp Image Segmentation","code":"https://github.com/hyunnamlee/RAPUNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"FCBFormer","metrics":{"mIoU":"0.8903","mean Dice":"0.9385"},"uses_additional_data":false,"paper_date":"2022-08-17","paper":"/paper/fcn-transformer-feature-fusion-for-polyp","paper_url":"https://arxiv.org/abs/2208.08352v1","paper_title":"FCN-Transformer Feature Fusion for Polyp Segmentation","code":"https://github.com/ESandML/FCBFormer","n_code_links":2,"syntology":null},{"rank_in_archive_order":11,"model":"HarDNet-DFUS","metrics":{"mIoU":"0.8894","mean Dice":"0.9363"},"uses_additional_data":false,"paper_date":"2022-09-15","paper":"/paper/hardnet-dfus-an-enhanced-harmonically","paper_url":"https://arxiv.org/abs/2209.07313v1","paper_title":"HarDNet-DFUS: An Enhanced Harmonically-Connected Network for Diabetic Foot Ulcer Image Segmentation and Colonoscopy Polyp Segmentation","code":"https://github.com/yuwenlo/hardnet-dfus","n_code_links":2,"syntology":null},{"rank_in_archive_order":12,"model":"SSFormer-L","metrics":{"mIoU":"0.8905","mean Dice":"0.9357"},"uses_additional_data":false,"paper_date":"2022-03-07","paper":"/paper/stepwise-feature-fusion-local-guides-global","paper_url":"https://arxiv.org/abs/2203.03635v3","paper_title":"Stepwise Feature Fusion: Local Guides Global","code":"https://github.com/Qiming-Huang/ssformer","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"FCBFormer","metrics":{"mean Dice":"0.932"},"uses_additional_data":false,"paper_date":"2024-12-17","paper":"/paper/s2s2-semantic-stacking-for-robust-semantic","paper_url":"https://arxiv.org/abs/2412.13156v1","paper_title":"S2S2: Semantic Stacking for Robust Semantic Segmentation in Medical Imaging","code":"https://github.com/ymp5078/semantic-stacking","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"ESFPNet-L","metrics":{"mIoU":"0.887","mean Dice":"0.931"},"uses_additional_data":false,"paper_date":"2022-07-15","paper":"/paper/esfpnet-efficient-deep-learning-architecture","paper_url":"https://arxiv.org/abs/2207.07759v3","paper_title":"ESFPNet: efficient deep learning architecture for real-time lesion segmentation in autofluorescence bronchoscopic video","code":"https://github.com/dumyCq/CFPNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"UGCANet","metrics":{"mIoU":"0.881","mean Dice":"0.928"},"uses_additional_data":false,"paper_date":"2023-07-12","paper":"/paper/ugcanet-a-unified-global-context-aware","paper_url":"https://arxiv.org/abs/2307.06260v1","paper_title":"UGCANet: A Unified Global Context-Aware Transformer-based Network with Feature Alignment for Endoscopic Image Analysis","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":16,"model":"EMCAD","metrics":{"mean Dice":"0.928"},"uses_additional_data":false,"paper_date":"2024-05-11","paper":"/paper/emcad-efficient-multi-scale-convolutional","paper_url":"https://arxiv.org/abs/2405.06880v1","paper_title":"EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentation","code":"https://github.com/sldgroup/emcad","n_code_links":1,"syntology":{"n_ran":20,"n_unverified":3,"n_samples":23,"n_pointer_only_licence":23}},{"rank_in_archive_order":17,"model":"PVT-GCASCADE","metrics":{"mIoU":"0.8790","mean Dice":"0.9274"},"uses_additional_data":false,"paper_date":"2023-10-24","paper":"/paper/g-cascade-efficient-cascaded-graph","paper_url":"https://arxiv.org/abs/2310.16175v1","paper_title":"G-CASCADE: Efficient Cascaded Graph Convolutional Decoding for 2D Medical Image Segmentation","code":"https://github.com/SLDGroup/G-CASCADE","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":3,"n_samples":9,"n_pointer_only_licence":9}},{"rank_in_archive_order":18,"model":"ColonFormer","metrics":{"mIoU":"0.877","mean Dice":"0.927"},"uses_additional_data":false,"paper_date":"2022-05-17","paper":"/paper/colonformer-an-efficient-transformer-based","paper_url":"https://arxiv.org/abs/2205.08473v3","paper_title":"ColonFormer: An Efficient Transformer based Method for Colon Polyp Segmentation","code":"https://github.com/ducnt9907/ColonFormer","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"RaBiT","metrics":{"mIoU":"0.873","mean Dice":"0.927"},"uses_additional_data":false,"paper_date":"2023-07-12","paper":"/paper/rabit-an-efficient-transformer-using","paper_url":"https://arxiv.org/abs/2307.06420v1","paper_title":"RaBiT: An Efficient Transformer using Bidirectional Feature Pyramid Network with Reverse Attention for Colon Polyp Segmentation","code":"https://github.com/nguyenhoangthuan99/RaBiT","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"GMSRF-Net","metrics":{"mIoU":"0.8843","mean Dice":"0.9263"},"uses_additional_data":false,"paper_date":"2021-11-20","paper":"/paper/gmsrf-net-an-improved-generalizability-with","paper_url":"https://arxiv.org/abs/2111.10614v1","paper_title":"GMSRF-Net: An improved generalizability with global multi-scale residual fusion network for polyp segmentation","code":"https://github.com/NoviceMAn-prog/GMSRFNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":21,"model":"PVT-CASCADE","metrics":{"mIoU":"0.8776","mean Dice":"0.9258"},"uses_additional_data":false,"paper_date":"2023-01-03","paper":"/paper/medical-image-segmentation-via-cascaded","paper_url":"https://openaccess.thecvf.com/content/WACV2023/html/Rahman_Medical_Image_Segmentation_via_Cascaded_Attention_Decoding_WACV_2023_paper.html","paper_title":"Medical Image Segmentation via Cascaded Attention Decoding","code":"https://github.com/SLDGroup/CASCADE","n_code_links":1,"syntology":null},{"rank_in_archive_order":22,"model":"DuAT","metrics":{"Average MAE":"0.023","mIoU":"0.876","mean Dice":"0.924"},"uses_additional_data":false,"paper_date":"2022-12-21","paper":"/paper/duat-dual-aggregation-transformer-network-for","paper_url":"https://arxiv.org/abs/2212.11677v1","paper_title":"DuAT: Dual-Aggregation Transformer Network for Medical Image Segmentation","code":"https://github.com/Barrett-python/DuAT","n_code_links":1,"syntology":null},{"rank_in_archive_order":23,"model":"MSRF-Net","metrics":{"mIoU":"0.8914","mean Dice":"0.9217"},"uses_additional_data":false,"paper_date":"2021-05-16","paper":"/paper/msrf-net-a-multi-scale-residual-fusion","paper_url":"https://arxiv.org/abs/2105.07451v2","paper_title":"MSRF-Net: A Multi-Scale Residual Fusion Network for Biomedical Image Segmentation","code":"https://github.com/NoviceMAn-prog/MSRF-Net","n_code_links":1,"syntology":null},{"rank_in_archive_order":24,"model":"ADSNet","metrics":{"mIoU":"0.871","mean Dice":"0.92"},"uses_additional_data":false,"paper_date":"2024-05-13","paper":"/paper/adaptation-of-distinct-semantics-for","paper_url":"https://arxiv.org/abs/2405.07523v1","paper_title":"Adaptation of Distinct Semantics for Uncertain Areas in Polyp Segmentation","code":"https://github.com/vinhhust2806/ADSNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":25,"model":"CaraNet","metrics":{"Average MAE":"0.023","S-Measure":"0.929","mIoU":"0.865","max E-Measure":"0.968","mean Dice":"0.918"},"uses_additional_data":false,"paper_date":"2021-08-16","paper":"/paper/caranet-context-axial-reverse-attention","paper_url":"https://arxiv.org/abs/2108.07368v3","paper_title":"CaraNet: Context Axial Reverse Attention Network for Segmentation of Small Medical Objects","code":"https://github.com/AngeLouCN/CaraNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":26,"model":"TransFuse-L","metrics":{"mIoU":"0.868","mean Dice":"0.918"},"uses_additional_data":false,"paper_date":"2021-02-16","paper":"/paper/transfuse-fusing-transformers-and-cnns-for","paper_url":"https://arxiv.org/abs/2102.08005v2","paper_title":"TransFuse: Fusing Transformers and CNNs for Medical Image Segmentation","code":"https://github.com/Rayicer/TransFuse","n_code_links":1,"syntology":null},{"rank_in_archive_order":27,"model":"TransFuse-S","metrics":{"mIoU":"0.868","mean Dice":"0.918"},"uses_additional_data":false,"paper_date":"2021-02-16","paper":"/paper/transfuse-fusing-transformers-and-cnns-for","paper_url":"https://arxiv.org/abs/2102.08005v2","paper_title":"TransFuse: Fusing Transformers and CNNs for Medical Image Segmentation","code":"https://github.com/Rayicer/TransFuse","n_code_links":1,"syntology":null},{"rank_in_archive_order":28,"model":"BDG-Net","metrics":{"Average MAE":"0.021","S-Measure":"0.923","mIoU":"0.865","max E-Measure":"0.972","mean Dice":"0.915"},"uses_additional_data":false,"paper_date":"2022-01-03","paper":"/paper/bdg-net-boundary-distribution-guided-network","paper_url":"https://arxiv.org/abs/2201.00767v2","paper_title":"BDG-Net: Boundary Distribution Guided Network for Accurate Polyp Segmentation","code":"https://github.com/zihuanqiu/BDG-Net","n_code_links":1,"syntology":null},{"rank_in_archive_order":29,"model":"SAM-EG","metrics":{"mIoU":"0.862","mean Dice":"0.915"},"uses_additional_data":false,"paper_date":"2024-06-21","paper":"/paper/sam-eg-segment-anything-model-with-egde","paper_url":"https://arxiv.org/abs/2406.14819v1","paper_title":"SAM-EG: Segment Anything Model with Egde Guidance framework for efficient Polyp Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":30,"model":"UniNet","metrics":{"mIoU":"0.857","mean Dice":"0.915"},"uses_additional_data":false,"paper_date":"2025-02-28","paper":"/paper/uninet-a-contrastive-learning-guided-unified","paper_url":"https://pangdatangtt.github.io/#:~:text=guided%20anomaly%20discrimination.-,Abstract,-Anomaly%20detection%20(AD","paper_title":"UniNet: A Contrastive Learning-guided Unified Framework with Feature Selection for Anomaly Detection","code":"https://github.com/pangdatangtt/UniNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":31,"model":"MEGANet(Res2Net-50)","metrics":{"Average MAE":"0.025","mIoU":"0.863","mean Dice":"0.913"},"uses_additional_data":false,"paper_date":"2023-09-06","paper":"/paper/meganet-multi-scale-edge-guided-attention","paper_url":"https://arxiv.org/abs/2309.03329v3","paper_title":"MEGANet: Multi-Scale Edge-Guided Attention Network for Weak Boundary Polyp Segmentation","code":"https://github.com/uark-aicv/meganet","n_code_links":2,"syntology":null},{"rank_in_archive_order":32,"model":"KDAS","metrics":{"Average MAE":"0.027","mIoU":"0.848","mean Dice":"0.913"},"uses_additional_data":false,"paper_date":"2023-12-13","paper":"/paper/kdas3-knowledge-distillation-via-attention","paper_url":"https://arxiv.org/abs/2312.08555v3","paper_title":"KDAS: Knowledge Distillation via Attention Supervision Framework for Polyp Segmentation","code":"https://github.com/huyquoctrinh/kdas","n_code_links":2,"syntology":null},{"rank_in_archive_order":33,"model":"HarDNet-MSEG","metrics":{"Average MAE":"0.025","FPS":"116","S-Measure":"0.923","mIoU":"0.857","max E-Measure":"0.958","mean Dice":"0.912"},"uses_additional_data":false,"paper_date":"2021-01-18","paper":"/paper/hardnet-mseg-a-simple-encoder-decoder-polyp","paper_url":"https://arxiv.org/abs/2101.07172v2","paper_title":"HarDNet-MSEG: A Simple Encoder-Decoder Polyp Segmentation Neural Network that Achieves over 0.9 Mean Dice and 86 FPS","code":"https://github.com/james128333/HarDNet-MSEG","n_code_links":4,"syntology":null},{"rank_in_archive_order":34,"model":"UACANet-L","metrics":{"Average MAE":"0.025","S-Measure":"0.917","mIoU":"0.862","max E-Measure":"0.958","mean Dice":"0.912"},"uses_additional_data":false,"paper_date":"2021-07-06","paper":"/paper/uacanet-uncertainty-augmented-context","paper_url":"https://arxiv.org/abs/2107.02368v3","paper_title":"UACANet: Uncertainty Augmented Context Attention for Polyp Segmentation","code":"https://github.com/plemeri/UACANet","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":35,"model":"MEGANet(ResNet-34)","metrics":{"Average MAE":"0.026","mIoU":"0.859","mean Dice":"0.911"},"uses_additional_data":false,"paper_date":"2023-09-06","paper":"/paper/meganet-multi-scale-edge-guided-attention","paper_url":"https://arxiv.org/abs/2309.03329v3","paper_title":"MEGANet: Multi-Scale Edge-Guided Attention Network for Weak Boundary Polyp Segmentation","code":"https://github.com/uark-aicv/meganet","n_code_links":2,"syntology":null},{"rank_in_archive_order":36,"model":"ProMISe","metrics":{"mIoU":"0.851","mean Dice":"0.911"},"uses_additional_data":false,"paper_date":"2024-03-07","paper":"/paper/promise-promptable-medical-image-segmentation","paper_url":"https://arxiv.org/abs/2403.04164v3","paper_title":"ProMISe: Promptable Medical Image Segmentation using SAM","code":"https://github.com/xinkunwang111/promise","n_code_links":1,"syntology":null},{"rank_in_archive_order":37,"model":"A-DenseUNet","metrics":{"mIoU":"0.8615","mean Dice":"0.9085"},"uses_additional_data":false,"paper_date":"2021-02-19","paper":"/paper/a-denseunet-adaptive-densely-connected-unet","paper_url":"https://www.mdpi.com/1424-8220/21/4/1441","paper_title":"A-DenseUNet: Adaptive Densely Connected UNet for Polyp Segmentation in Colonoscopy Images with Atrous Convolution","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":38,"model":"UACANet-S","metrics":{"Average MAE":"0.026","S-Measure":"0.914","mIoU":"0.852","max E-Measure":"0.951","mean Dice":"0.905"},"uses_additional_data":false,"paper_date":"2021-07-06","paper":"/paper/uacanet-uncertainty-augmented-context","paper_url":"https://arxiv.org/abs/2107.02368v3","paper_title":"UACANet: Uncertainty Augmented Context Attention for Polyp Segmentation","code":"https://github.com/plemeri/UACANet","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":39,"model":"COMMA (ResNet-50)","metrics":{"Average MAE":"0.024","S-Measure":"0.925","mIoU":"0.860","max E-Measure":"0.963","mean Dice":"0.904"},"uses_additional_data":false,"paper_date":"2022-02-17","paper":"/paper/comma-propagating-complementary-multi-level","paper_url":"https://www.mdpi.com/2076-3417/12/4/2114","paper_title":"COMMA: Propagating Complementary Multi-Level Aggregation Network for Polyp Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":40,"model":"Polyp-SAM++","metrics":{"F-measure":"0.92","mIoU":"0.862","mean Dice":"0.902"},"uses_additional_data":false,"paper_date":"2023-08-12","paper":"/paper/polyp-sam-can-a-text-guided-sam-perform","paper_url":"https://arxiv.org/abs/2308.06623v1","paper_title":"Polyp-SAM++: Can A Text Guided SAM Perform Better for Polyp Segmentation?","code":"https://github.com/RisabBiswas/Polyp-SAM-PlusPlus","n_code_links":2,"syntology":null},{"rank_in_archive_order":41,"model":"AG-CUResNeSt","metrics":{"mIoU":"0.845","mean Dice":"0.902"},"uses_additional_data":false,"paper_date":"2021-05-02","paper":"/paper/ag-curesnest-a-novel-method-for-colon-polyp","paper_url":"https://arxiv.org/abs/2105.00402v3","paper_title":"AG-CUResNeSt: A Novel Method for Colon Polyp Segmentation","code":"https://github.com/code-implementation1/Code9/tree/main/resnest","n_code_links":1,"syntology":null},{"rank_in_archive_order":42,"model":"COMMA (Res2Net-50)","metrics":{"Average MAE":"0.027","S-Measure":"0.919","mIoU":"0.852","max E-Measure":"0.951","mean Dice":"0.901"},"uses_additional_data":false,"paper_date":"2022-02-17","paper":"/paper/comma-propagating-complementary-multi-level","paper_url":"https://www.mdpi.com/2076-3417/12/4/2114","paper_title":"COMMA: Propagating Complementary Multi-Level Aggregation Network for Polyp Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":43,"model":"TGA-Net","metrics":{"mIoU":"0.8330","mean Dice":"0.8982"},"uses_additional_data":false,"paper_date":"2022-05-09","paper":"/paper/tganet-text-guided-attention-for-improved","paper_url":"https://arxiv.org/abs/2205.04280v1","paper_title":"TGANet: Text-guided attention for improved polyp segmentation","code":"https://github.com/nikhilroxtomar/tganet","n_code_links":1,"syntology":null},{"rank_in_archive_order":44,"model":"PraNet","metrics":{"Average MAE":"0.030","S-Measure":"0.915","mIoU":"0.849","max E-Measure":"0.948","mean Dice":"0.898"},"uses_additional_data":false,"paper_date":"2020-06-13","paper":"/paper/pranet-parallel-reverse-attention-network-for","paper_url":"https://arxiv.org/abs/2006.11392v4","paper_title":"PraNet: Parallel Reverse Attention Network for Polyp Segmentation","code":"https://github.com/DengPingFan/PraNet","n_code_links":4,"syntology":{"n_ran":0,"n_unverified":9,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":45,"model":"TransResU-Net","metrics":{"FPS":"48.61","mIoU":"0.8214","mean Dice":"0.8884"},"uses_additional_data":false,"paper_date":"2022-06-17","paper":"/paper/transresu-net-transformer-based-resu-net-for","paper_url":"https://arxiv.org/abs/2206.08985v1","paper_title":"TransResU-Net: Transformer based ResU-Net for Real-Time Colonoscopy Polyp Segmentation","code":"https://github.com/nikhilroxtomar/transresunet","n_code_links":1,"syntology":null},{"rank_in_archive_order":46,"model":"PEFNet","metrics":{"mIoU":"0.8163","mean Dice":"0.8818"},"uses_additional_data":false,"paper_date":"2023-01-17","paper":"/paper/multi-kernel-positional-embedding-convnext","paper_url":"https://arxiv.org/abs/2301.06673v2","paper_title":"Multi Kernel Positional Embedding ConvNeXt for Polyp Segmentation","code":"https://github.com/huyquoctrinh/PEFNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":47,"model":"FANet","metrics":{"Average MAE":"0.8153","mean Dice":"0.8803"},"uses_additional_data":false,"paper_date":"2021-03-31","paper":"/paper/fanet-a-feedback-attention-network-for","paper_url":"https://arxiv.org/abs/2103.17235v3","paper_title":"FANet: A Feedback Attention Network for Improved Biomedical Image Segmentation","code":"https://github.com/nikhilroxtomar/fanet","n_code_links":1,"syntology":null},{"rank_in_archive_order":48,"model":"TransNetR","metrics":{"FPS":"54.60","mIoU":"0.8016","mean Dice":"0.8706"},"uses_additional_data":false,"paper_date":"2023-03-13","paper":"/paper/transnetr-transformer-based-residual-network","paper_url":"https://arxiv.org/abs/2303.07428v1","paper_title":"TransNetR: Transformer-based Residual Network for Polyp Segmentation with Multi-Center Out-of-Distribution Testing","code":"https://github.com/debeshjha/transnetr","n_code_links":1,"syntology":null},{"rank_in_archive_order":49,"model":"Yolo-SAM 2","metrics":{"mIoU":"0.764","mean Dice":"0.866"},"uses_additional_data":false,"paper_date":"2024-09-14","paper":"/paper/self-prompting-polyp-segmentation-in","paper_url":"https://arxiv.org/abs/2409.09484v1","paper_title":"Self-Prompting Polyp Segmentation in Colonoscopy using Hybrid Yolo-SAM 2 Model","code":"https://github.com/sajjad-sh33/yolo_sam2","n_code_links":1,"syntology":null},{"rank_in_archive_order":50,"model":"DDANet","metrics":{"FPS":"69.59","mIoU":"0.7800","mean Dice":"0.8576"},"uses_additional_data":false,"paper_date":"2020-12-30","paper":"/paper/ddanet-dual-decoder-attention-network-for","paper_url":"https://arxiv.org/abs/2012.15245v1","paper_title":"DDANet: Dual Decoder Attention Network for Automatic Polyp Segmentation","code":"https://github.com/nikhilroxtomar/DDANet","n_code_links":1,"syntology":null},{"rank_in_archive_order":51,"model":"DoubleUnet-DCA","metrics":{"mIoU":"0.7434","mean Dice":"0.8516"},"uses_additional_data":false,"paper_date":"2023-03-30","paper":"/paper/dual-cross-attention-for-medical-image","paper_url":"https://arxiv.org/abs/2303.17696v1","paper_title":"Dual Cross-Attention for Medical Image Segmentation","code":"https://github.com/gorkemcanates/dual-cross-attention","n_code_links":1,"syntology":null},{"rank_in_archive_order":52,"model":"ResUNet++ + TTA + CRF","metrics":{"FPS":"69.59","mIoU":"0.7800","mean Dice":"0.8508"},"uses_additional_data":false,"paper_date":"2021-07-26","paper":"/paper/a-comprehensive-study-on-colorectal-polyp","paper_url":"https://arxiv.org/abs/2107.12435v1","paper_title":"A Comprehensive Study on Colorectal Polyp Segmentation with ResUNet++, Conditional Random Field and Test-Time Augmentation","code":"https://github.com/DebeshJha/ResUNet-with-CRF-and-TTA","n_code_links":1,"syntology":null},{"rank_in_archive_order":53,"model":"U-Net++","metrics":{"Average MAE":"0.048","S-Measure":"0.862","max E-Measure":"0.910","mean Dice":"0.8210"},"uses_additional_data":false,"paper_date":"2018-07-18","paper":"/paper/unet-a-nested-u-net-architecture-for-medical","paper_url":"http://arxiv.org/abs/1807.10165v1","paper_title":"UNet++: A Nested U-Net Architecture for Medical Image Segmentation","code":"https://github.com/qubvel/segmentation_models.pytorch","n_code_links":34,"syntology":{"n_ran":5,"n_unverified":23,"n_samples":28,"n_pointer_only_licence":2}},{"rank_in_archive_order":54,"model":"ColonSegNet","metrics":{"FPS":"182.38","mIoU":"0.7239","mean Dice":"0.8206"},"uses_additional_data":false,"paper_date":"2020-11-15","paper":"/paper/real-time-polyp-detection-localisation-and","paper_url":"https://arxiv.org/abs/2011.07631v2","paper_title":"Real-Time Polyp Detection, Localization and Segmentation in Colonoscopy Using Deep Learning","code":"https://github.com/DebeshJha/ColonSegNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":55,"model":"U-Net","metrics":{"Average MAE":"0.055","S-Measure":"0.858","max E-Measure":"0.893","mean Dice":"0.8180"},"uses_additional_data":false,"paper_date":"2015-05-18","paper":"/paper/u-net-convolutional-networks-for-biomedical","paper_url":"http://arxiv.org/abs/1505.04597v1","paper_title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","code":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","n_code_links":487,"syntology":{"n_ran":510,"n_unverified":247,"n_samples":757,"n_pointer_only_licence":426}},{"rank_in_archive_order":56,"model":"ResUNet++","metrics":{"mean Dice":"0.8133"},"uses_additional_data":false,"paper_date":"2019-11-16","paper":"/paper/resunet-an-advanced-architecture-for-medical","paper_url":"https://arxiv.org/abs/1911.07067v1","paper_title":"ResUNet++: An Advanced Architecture for Medical Image Segmentation","code":"https://github.com/rishikksh20/ResUnet","n_code_links":6,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":4}},{"rank_in_archive_order":57,"model":"ResUNet","metrics":{"mean Dice":"0.7877"},"uses_additional_data":false,"paper_date":"2019-11-16","paper":"/paper/kvasir-seg-a-segmented-polyp-dataset","paper_url":"https://arxiv.org/abs/1911.07069v1","paper_title":"Kvasir-SEG: A Segmented Polyp Dataset","code":"https://github.com/tfboys-lzz/fobs","n_code_links":1,"syntology":null},{"rank_in_archive_order":58,"model":"RUPNet","metrics":{"FPS":"152.60","mIoU":"0.6553","mean Dice":"0.7658"},"uses_additional_data":false,"paper_date":"2023-01-06","paper":"/paper/rupnet-residual-upsampling-network-for-real","paper_url":"https://arxiv.org/abs/2301.02703v2","paper_title":"RUPNet: Residual upsampling network for real-time polyp segmentation","code":null,"n_code_links":0,"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,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":8,"rows_with_any_sample_ran":7,"distinct_papers_with_graph_line":7,"distinct_papers_with_any_sample_ran":6,"samples_over_distinct_papers":{"n_ran":544,"n_unverified":290,"n_samples":834,"n_pointer_only_licence":464,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":545,"n_unverified":293,"n_samples":838,"n_pointer_only_licence":464,"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"}}}