[ { "Mean IoU": 81.7, "code_links": [ { "title": "NVIDIA/semantic-segmentation", "url": "https://github.com/NVIDIA/semantic-segmentation" } ], "date": "2018-12-04", "date2": 20181204, "model": "DeepLabV3Plus + SDCNetAug", "paper": { "title": "Improving Semantic Segmentation via Video Propagation and Label Relaxation", "url": "https://cknow.io/lib/d18292324b9cbac0" }, "paper_data_uoa": "d18292324b9cbac0" }, { "Mean IoU": 78.47, "code_links": [ { "title": "leoxiaobin/deep-high-resolution-net.pytorch", "url": "https://github.com/leoxiaobin/deep-high-resolution-net.pytorch" }, { "title": "HRNet/HRNet-Semantic-Segmentation", "url": "https://github.com/HRNet/HRNet-Semantic-Segmentation" }, { "title": "HRNet/HRNet-Object-Detection", "url": "https://github.com/HRNet/HRNet-Object-Detection" }, { "title": "HRNet/HRNet-Image-Classification", "url": "https://github.com/HRNet/HRNet-Image-Classification" }, { "title": "HRNet/HRNet-Facial-Landmark-Detection", "url": "https://github.com/HRNet/HRNet-Facial-Landmark-Detection" }, { "title": "HRNet/HRNet-MaskRCNN-Benchmark", "url": "https://github.com/HRNet/HRNet-MaskRCNN-Benchmark" } ], "date": "2019-08-20", "date2": 20190820, "model": "HRNetV2 (HRNetV2-W48)", "paper": { "title": "Deep High-Resolution Representation Learning for Visual Recognition", "url": "https://cknow.io/lib/a907f44d2b3b200a" }, "paper_data_uoa": "a907f44d2b3b200a" }, { "Mean IoU": 69.1, "code_links": [ { "title": "tensorflow/models", "url": "https://github.com/tensorflow/models/tree/master/research/deeplab" }, { "title": "CSAILVision/semantic-segmentation-pytorch", "url": "https://github.com/CSAILVision/semantic-segmentation-pytorch" }, { "title": "qubvel/segmentation_models", "url": "https://github.com/qubvel/segmentation_models" }, { "title": "divamgupta/image-segmentation-keras", "url": "https://github.com/divamgupta/image-segmentation-keras" }, { "title": "osmr/imgclsmob", "url": "https://github.com/osmr/imgclsmob" }, { "title": "hszhao/PSPNet", "url": "https://github.com/hszhao/PSPNet" }, { "title": "warmspringwinds/pytorch-segmentation-detection", "url": "https://github.com/warmspringwinds/pytorch-segmentation-detection" }, { "title": "y-ouali/pytorch_segmentation", "url": "https://github.com/y-ouali/pytorch_segmentation" }, { "title": "PRBonn/bonnet", "url": "https://github.com/PRBonn/bonnet" }, { "title": "manideep2510/eye-in-the-sky", "url": "https://github.com/manideep2510/eye-in-the-sky" }, { "title": "switchablenorms/SwitchNorm_Segmentation", "url": "https://github.com/switchablenorms/SwitchNorm_Segmentation" }, { "title": "kazuto1011/pspnet-pytorch", "url": "https://github.com/kazuto1011/pspnet-pytorch" }, { "title": "BOBrown/deeparsing-master", "url": "https://github.com/BOBrown/deeparsing-master" }, { "title": "jqueguiner/camembert-as-a-service", "url": "https://github.com/jqueguiner/camembert-as-a-service" }, { "title": "jqueguiner/image-segmentation", "url": "https://github.com/jqueguiner/image-segmentation" }, { "title": "kukby/Mish-semantic-segmentation-pytorch", "url": "https://github.com/kukby/Mish-semantic-segmentation-pytorch" }, { "title": "udacity/MLND-CN-Capstone-TGSImage", "url": "https://github.com/udacity/MLND-CN-Capstone-TGSImage" }, { "title": "leemathew1998/RG", "url": "https://github.com/leemathew1998/RG" }, { "title": "RituYadav92/Image-segmentation", "url": "https://github.com/RituYadav92/Image-segmentation" }, { "title": "monsieurmona/LinkCollectionAutonomousDriving", "url": "https://github.com/monsieurmona/LinkCollectionAutonomousDriving" }, { "title": "leemathew1998/GradientWeight", "url": "https://github.com/leemathew1998/GradientWeight" }, { "title": "RRoundTable/U_net", "url": "https://github.com/RRoundTable/U_net" }, { "title": "Lxrd-AJ/Advanced_ML", "url": "https://github.com/Lxrd-AJ/Advanced_ML" } ], "date": "2016-12-04", "date2": 20161204, "model": "PSPNet", "paper": { "title": "Pyramid Scene Parsing Network", "url": "https://cknow.io/lib/59c987cd01bc78f7" }, "paper_data_uoa": "59c987cd01bc78f7" }, { "Mean IoU": 68.7, "code_links": [ { "title": "ycszen/TorchSeg", "url": "https://github.com/ycszen/TorchSeg" }, { "title": "ooooverflow/BiSeNet", "url": "https://github.com/ooooverflow/BiSeNet" }, { "title": "ycszen/BiSeNet", "url": "https://github.com/ycszen/BiSeNet" }, { "title": "kirilcvetkov92/Semantic-Segmentation", "url": "https://github.com/kirilcvetkov92/Semantic-Segmentation" }, { "title": "pdoublerainbow/bisenet-tensorflow", "url": "https://github.com/pdoublerainbow/bisenet-tensorflow" }, { "title": "Blaizzy/BiSeNet-Implementation", "url": "https://github.com/Blaizzy/BiSeNet-Implementation" }, { "title": "GuangyanZhang/SCNN-Deeplabv3-bisenet-icnet", "url": "https://github.com/GuangyanZhang/SCNN-Deeplabv3-bisenet-icnet" }, { "title": "Shuai-Xie/BiSeNet-CCP", "url": "https://github.com/Shuai-Xie/BiSeNet-CCP" } ], "date": "2018-08-02", "date2": 20180802, "model": "BiSeNet", "paper": { "title": "BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation", "url": "https://cknow.io/lib/7f0020f42ac91801" }, "paper_data_uoa": "7f0020f42ac91801" }, { "Global Accuracy": 91.5, "Mean IoU": 66.9, "code_links": [ { "title": "SimJeg/FC-DenseNet", "url": "https://github.com/SimJeg/FC-DenseNet" }, { "title": "0bserver07/One-Hundred-Layers-Tiramisu", "url": "https://github.com/0bserver07/One-Hundred-Layers-Tiramisu" }, { "title": "Kaido0/Brain-Tissue-Segment-Keras", "url": "https://github.com/Kaido0/Brain-Tissue-Segment-Keras" }, { "title": "petko-nikolov/pysemseg", "url": "https://github.com/petko-nikolov/pysemseg" }, { "title": "asprenger/keras_fc_densenet", "url": "https://github.com/asprenger/keras_fc_densenet" }, { "title": "smdYe/FC-DenseNet-Keras", "url": "https://github.com/smdYe/FC-DenseNet-Keras" }, { "title": "pattyhendrix/CamVid-95-accuracy", "url": "https://github.com/pattyhendrix/CamVid-95-accuracy" }, { "title": "demul/image_segmentation_project", "url": "https://github.com/demul/image_segmentation_project" }, { "title": "Septembit/Image-segmentation", "url": "https://github.com/Septembit/Image-segmentation" }, { "title": "noornk/U-Net", "url": "https://github.com/noornk/U-Net" }, { "title": "koryako/AI-application", "url": "https://github.com/koryako/AI-application" }, { "title": "ankit-vaghela30/Cilia-Segmentation", "url": "https://github.com/ankit-vaghela30/Cilia-Segmentation" } ], "date": "2016-11-28", "date2": 20161128, "model": "FC-DenseNet103", "paper": { "title": "The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation", "url": "https://cknow.io/lib/85e3ce417c89d4db" }, "paper_data_uoa": "85e3ce417c89d4db" }, { "Mean IoU": 65.3, "code_links": [ { "title": "fyu/dilation", "url": "https://github.com/fyu/dilation" }, { "title": "vlievin/Unet", "url": "https://github.com/vlievin/Unet" }, { "title": "Wanger-SJTU/FCN-in-the-wild", "url": "https://github.com/Wanger-SJTU/FCN-in-the-wild" }, { "title": "lpzjerry/Pedestrian-Attribute-LGNet", "url": "https://github.com/lpzjerry/Pedestrian-Attribute-LGNet" }, { "title": "keillernogueira/FDSI", "url": "https://github.com/keillernogueira/FDSI" }, { "title": "Entodi/meshnet-pytorch", "url": "https://github.com/Entodi/meshnet-pytorch" }, { "title": "srihari-humbarwadi/Multi-Scale-Context-Aggregation-by-Dilated-Convolutions", "url": "https://github.com/srihari-humbarwadi/Multi-Scale-Context-Aggregation-by-Dilated-Convolutions" }, { "title": "Rakeshpavan333/oct_dil", "url": "https://github.com/Rakeshpavan333/oct_dil" }, { "title": "harshmaru7/DilatedConv", "url": "https://github.com/harshmaru7/DilatedConv" } ], "date": "2015-11-23", "date2": 20151123, "model": "Dilated Convolutions", "paper": { "title": "Multi-Scale Context Aggregation by Dilated Convolutions", "url": "https://cknow.io/lib/eab0185455d90cf6" }, "paper_data_uoa": "eab0185455d90cf6" }, { "Mean IoU": 61.6, "code_links": [ { "title": "tensorflow/models", "url": "https://github.com/tensorflow/models/tree/master/research/deeplab" }, { "title": "DeepMotionAIResearch/DenseASPP", "url": "https://github.com/DeepMotionAIResearch/DenseASPP" }, { "title": "arahusky/Tensorflow-Segmentation", "url": "https://github.com/arahusky/Tensorflow-Segmentation" }, { "title": "nightrome/cocostuff10k", "url": "https://github.com/nightrome/cocostuff10k" }, { "title": "TheLegendAli/DeepLab-Context", "url": "https://github.com/TheLegendAli/DeepLab-Context" }, { "title": "BardOfCodes/pytorch_deeplab_large_fov", "url": "https://github.com/BardOfCodes/pytorch_deeplab_large_fov" }, { "title": "wangleihitcs/DeepLab-V1-PyTorch", "url": "https://github.com/wangleihitcs/DeepLab-V1-PyTorch" }, { "title": "open-cv/deeplab-v1", "url": "https://github.com/open-cv/deeplab-v1" } ], "date": "2014-12-22", "date2": 20141222, "model": "DeepLab-MSc-CRF-LargeFOV", "paper": { "title": "Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs", "url": "https://cknow.io/lib/974f0dbe4b927ae5" }, "paper_data_uoa": "974f0dbe4b927ae5" }, { "Global Accuracy": 88.7, "Mean IoU": 58.8, "code_links": [ { "title": "fvisin/reseg", "url": "https://github.com/fvisin/reseg" }, { "title": "SConsul/ReSeg", "url": "https://github.com/SConsul/ReSeg" } ], "date": "2015-11-22", "date2": 20151122, "model": "ReSeg", "paper": { "title": "ReSeg: A Recurrent Neural Network-based Model for Semantic Segmentation", "url": "https://cknow.io/lib/52f69344979c41b8" }, "paper_data_uoa": "52f69344979c41b8" }, { "Mean IoU": 46.4, "code_links": [ { "title": "divamgupta/image-segmentation-keras", "url": "https://github.com/divamgupta/image-segmentation-keras" }, { "title": "alexgkendall/caffe-segnet", "url": "https://github.com/alexgkendall/caffe-segnet" }, { "title": "alexgkendall/SegNet-Tutorial", "url": "https://github.com/alexgkendall/SegNet-Tutorial" }, { "title": "tkuanlun350/Tensorflow-SegNet", "url": "https://github.com/tkuanlun350/Tensorflow-SegNet" }, { "title": "y-ouali/pytorch_segmentation", "url": "https://github.com/y-ouali/pytorch_segmentation" }, { "title": "PRBonn/bonnet", "url": "https://github.com/PRBonn/bonnet" }, { "title": "arahusky/Tensorflow-Segmentation", "url": "https://github.com/arahusky/Tensorflow-Segmentation" }, { "title": "navganti/SIVO", "url": "https://github.com/navganti/SIVO" }, { "title": "preddy5/segnet", "url": "https://github.com/preddy5/segnet" }, { "title": "TimoSaemann/caffe-segnet-cudnn5", "url": "https://github.com/TimoSaemann/caffe-segnet-cudnn5" }, { "title": "vqdang/xy_net", "url": "https://github.com/vqdang/xy_net" }, { "title": "vqdang/hover_net", "url": "https://github.com/vqdang/hover_net" }, { "title": "JosephPB/XNet", "url": "https://github.com/JosephPB/XNet" }, { "title": "ankit-ai/GAN_breast_mammography_segmentation", "url": "https://github.com/ankit-ai/GAN_breast_mammography_segmentation" }, { "title": "neuropoly/multiclass-segmentation", "url": "https://github.com/neuropoly/multiclass-segmentation" }, { "title": "ArkaJU/SegNet---Chromosome", "url": "https://github.com/ArkaJU/SegNet---Chromosome" }, { "title": "Lkruitwagen/remote-sensing-solar-pv", "url": "https://github.com/Lkruitwagen/remote-sensing-solar-pv" }, { "title": "jqueguiner/camembert-as-a-service", "url": "https://github.com/jqueguiner/camembert-as-a-service" }, { "title": "yinanzhu12/SegNet-keras-implementation", "url": "https://github.com/yinanzhu12/SegNet-keras-implementation" }, { "title": "yinanzhu12/SegNet-keras", "url": "https://github.com/yinanzhu12/SegNet-keras" }, { "title": "jqueguiner/image-segmentation", "url": "https://github.com/jqueguiner/image-segmentation" }, { "title": "alejandrodebus/SegNet", "url": "https://github.com/alejandrodebus/SegNet" }, { "title": "arsalhuda24/SS_lstm", "url": "https://github.com/arsalhuda24/SS_lstm" }, { "title": "XiangbingJi/Stanford-cs230-final-project", "url": "https://github.com/XiangbingJi/Stanford-cs230-final-project" }, { "title": "Tez01/SegNet-Keras-Implementation", "url": "https://github.com/Tez01/SegNet-Keras-Implementation" }, { "title": "falreis/segmentation-eval", "url": "https://github.com/falreis/segmentation-eval" }, { "title": "hosshonarvar/Image-Segmentation", "url": "https://github.com/hosshonarvar/Image-Segmentation" }, { "title": "tday01/CS193-Project", "url": "https://github.com/tday01/CS193-Project" }, { "title": "s9mondal9upriti/Segnet", "url": "https://github.com/s9mondal9upriti/Segnet" }, { "title": "rotemgoren/segNet", "url": "https://github.com/rotemgoren/segNet" }, { "title": "ajjdan/KaI", "url": "https://github.com/ajjdan/KaI" }, { "title": "navganti/SegNet", "url": "https://github.com/navganti/SegNet" }, { "title": "resonance20/segmenter", "url": "https://github.com/resonance20/segmenter" }, { "title": "alexandrelewin/FollowMe", "url": "https://github.com/alexandrelewin/FollowMe" }, { "title": "Zhanghongbin-github/SegNet-Tutorial", "url": "https://github.com/Zhanghongbin-github/SegNet-Tutorial" }, { "title": "HAN-ARK/GVSS-S.A.Drone", "url": "https://github.com/HAN-ARK/GVSS-S.A.Drone" }, { "title": "amaurylekens/SDC_Segnet", "url": "https://github.com/amaurylekens/SDC_Segnet" }, { "title": "NeuronDroid/GVSS-S.A.Drone", "url": "https://github.com/NeuronDroid/GVSS-S.A.Drone" }, { "title": "TqDavid/td", "url": "https://github.com/TqDavid/td" }, { "title": "RajkumarPreetham/Road-scene-understanding", "url": "https://github.com/RajkumarPreetham/Road-scene-understanding" }, { "title": "billlyzhaoyh/SegNetFromScratch", "url": "https://github.com/billlyzhaoyh/SegNetFromScratch" }, { "title": "DarkGeekMS/Semantic_Segmentation_Models_Keras", "url": "https://github.com/DarkGeekMS/Semantic_Segmentation_Models_Keras" }, { "title": "okn-yu/SegNet-A-Deep-Convolutional-Encoder-Decoder-Architecture-for-Image-Segmentation", "url": "https://github.com/okn-yu/SegNet-A-Deep-Convolutional-Encoder-Decoder-Architecture-for-Image-Segmentation" } ], "date": "2015-11-02", "date2": 20151102, "model": "SegNet", "paper": { "title": "SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation", "url": "https://cknow.io/lib/2b85472fa0314713" }, "paper_data_uoa": "2b85472fa0314713" } ]