Awesome Semantic Segmentation

Networks by architecture

Semantic segmentation

• U-Net [https://arxiv.org/pdf/1505.04597.pdf] [2015]
  • https://github.com/zhixuhao/unet [Keras]
  • https://github.com/jocicmarko/ultrasound-nerve-segmentation [Keras]
  • https://github.com/EdwardTyantov/ultrasound-nerve-segmentation [Keras]
  • https://github.com/ZFTurbo/ZF_UNET_224_Pretrained_Model [Keras]
  • https://github.com/yihui-he/u-net [Keras]
  • https://github.com/jakeret/tf_unet [Tensorflow]
  • https://github.com/divamgupta/image-segmentation-keras [Keras]
  • https://github.com/ZijunDeng/pytorch-semantic-segmentation [PyTorch]
  • https://github.com/akirasosa/mobile-semantic-segmentation [Keras]
  • https://github.com/orobix/retina-unet [Keras]
  • https://github.com/qureai/ultrasound-nerve-segmentation-using-torchnet [Torch]
  • https://github.com/ternaus/TernausNet [PyTorch]
  • https://github.com/qubvel/segmentation_models [Keras]
  • https://github.com/LeeJunHyun/Image_Segmentation#u-net [PyTorch]
  • https://github.com/yassouali/pytorch_segmentation [PyTorch]
  • https://lmb.informatik.uni-freiburg.de/people/ronneber/u-net/ [Caffe + Matlab]
• SegNet [https://arxiv.org/pdf/1511.00561.pdf] [2016]
  • https://github.com/alexgkendall/caffe-segnet [Caffe]
  • https://github.com/developmentseed/caffe/tree/segnet-multi-gpu [Caffe]
  • https://github.com/preddy5/segnet [Keras]
  • https://github.com/imlab-uiip/keras-segnet [Keras]
  • https://github.com/andreaazzini/segnet [Tensorflow]
  • https://github.com/fedor-chervinskii/segnet-torch [Torch]
  • https://github.com/0bserver07/Keras-SegNet-Basic [Keras]
  • https://github.com/tkuanlun350/Tensorflow-SegNet [Tensorflow]
  • https://github.com/divamgupta/image-segmentation-keras [Keras]
  • https://github.com/ZijunDeng/pytorch-semantic-segmentation [PyTorch]
  • https://github.com/chainer/chainercv/tree/master/examples/segnet [Chainer]
  • https://github.com/ykamikawa/keras-SegNet [Keras]
  • https://github.com/ykamikawa/tf-keras-SegNet [Keras]
  • https://github.com/yassouali/pytorch_segmentation [PyTorch]
• DeepLab [https://arxiv.org/pdf/1606.00915.pdf] [2017]
  • https://bitbucket.org/deeplab/deeplab-public/ [Caffe]
  • https://bitbucket.org/aquariusjay/deeplab-public-ver2 [Caffe]
  • https://github.com/TheLegendAli/DeepLab-Context [Caffe]
  • https://github.com/msracver/Deformable-ConvNets/tree/master/deeplab [MXNet]
  • https://github.com/DrSleep/tensorflow-deeplab-resnet [Tensorflow]
  • https://github.com/muyang0320/tensorflow-deeplab-resnet-crf [TensorFlow]
  • https://github.com/isht7/pytorch-deeplab-resnet [PyTorch]
  • https://github.com/bermanmaxim/jaccardSegment [PyTorch]
  • https://github.com/martinkersner/train-DeepLab [Caffe]
  • https://github.com/chenxi116/TF-deeplab [Tensorflow]
  • https://github.com/bonlime/keras-deeplab-v3-plus [Keras]
  • https://github.com/tensorflow/models/tree/master/research/deeplab [Tensorflow]
  • https://github.com/speedinghzl/pytorch-segmentation-toolbox [PyTorch]
  • https://github.com/kazuto1011/deeplab-pytorch [PyTorch]
  • https://github.com/youansheng/torchcv [PyTorch]
  • https://github.com/yassouali/pytorch_segmentation [PyTorch]
  • https://github.com/hualin95/Deeplab-v3plus [PyTorch]
• FCN [https://arxiv.org/pdf/1605.06211.pdf] [2016]
  • https://github.com/vlfeat/matconvnet-fcn [MatConvNet]
  • https://github.com/shelhamer/fcn.berkeleyvision.org [Caffe]
  • https://github.com/MarvinTeichmann/tensorflow-fcn [Tensorflow]
  • https://github.com/aurora95/Keras-FCN [Keras]
  • https://github.com/mzaradzki/neuralnets/tree/master/vgg_segmentation_keras [Keras]
  • https://github.com/k3nt0w/FCN_via_keras [Keras]
  • https://github.com/shekkizh/FCN.tensorflow [Tensorflow]
  • https://github.com/seewalker/tf-pixelwise [Tensorflow]
  • https://github.com/divamgupta/image-segmentation-keras [Keras]
  • https://github.com/ZijunDeng/pytorch-semantic-segmentation [PyTorch]
  • https://github.com/wkentaro/pytorch-fcn [PyTorch]
  • https://github.com/wkentaro/fcn [Chainer]
  • https://github.com/apache/incubator-mxnet/tree/master/example/fcn-xs [MxNet]
  • https://github.com/muyang0320/tf-fcn [Tensorflow]
  • https://github.com/ycszen/pytorch-seg [PyTorch]
  • https://github.com/Kaixhin/FCN-semantic-segmentation [PyTorch]
  • https://github.com/petrama/VGGSegmentation [Tensorflow]
  • https://github.com/simonguist/testing-fcn-for-cityscapes [Caffe]
  • https://github.com/hellochick/semantic-segmentation-tensorflow [Tensorflow]
  • https://github.com/pierluigiferrari/fcn8s_tensorflow [Tensorflow]
  • https://github.com/theduynguyen/Keras-FCN [Keras]
  • https://github.com/JihongJu/keras-fcn [Keras]
  • https://github.com/yassouali/pytorch_segmentation [PyTorch]
• ENet [https://arxiv.org/pdf/1606.02147.pdf] [2016]
  • https://github.com/TimoSaemann/ENet [Caffe]
  • https://github.com/e-lab/ENet-training [Torch]
  • https://github.com/PavlosMelissinos/enet-keras [Keras]
  • https://github.com/fregu856/segmentation [Tensorflow]
  • https://github.com/kwotsin/TensorFlow-ENet [Tensorflow]
  • https://github.com/davidtvs/PyTorch-ENet [PyTorch]
  • https://github.com/yassouali/pytorch_segmentation [PyTorch]
• LinkNet [https://arxiv.org/pdf/1707.03718.pdf] [2017]
  • https://github.com/e-lab/LinkNet [Torch]
  • https://github.com/qubvel/segmentation_models [Keras]
• DenseNet [https://arxiv.org/pdf/1611.09326.pdf] [2017]
  • https://github.com/SimJeg/FC-DenseNet [Lasagne]
  • https://github.com/HasnainRaz/FC-DenseNet-TensorFlow [Tensorflow]
  • https://github.com/0bserver07/One-Hundred-Layers-Tiramisu [Keras]
• DilatedNet [https://arxiv.org/pdf/1511.07122.pdf] [2016]
  • https://github.com/nicolov/segmentation_keras [Keras]
  • https://github.com/fyu/dilation [Caffe]
  • https://github.com/fyu/drn#semantic-image-segmentataion [PyTorch]
  • https://github.com/hangzhaomit/semantic-segmentation-pytorch [PyTorch]
• PixelNet [https://arxiv.org/pdf/1609.06694.pdf] [2016]
  • https://github.com/aayushbansal/PixelNet [Caffe]
• ICNet [https://arxiv.org/pdf/1704.08545.pdf] [2017]
  • https://github.com/hszhao/ICNet [Caffe]
  • https://github.com/aitorzip/Keras-ICNet [Keras]
  • https://github.com/hellochick/ICNet-tensorflow [Tensorflow]
  • https://github.com/oandrienko/fast-semantic-segmentation [Tensorflow]
  • https://github.com/supervisely/supervisely/tree/master/plugins/nn/icnet [PyTorch]
• ERFNet [http://www.robesafe.uah.es/personal/eduardo.romera/pdfs/Romera17iv.pdf] [?]
  • https://github.com/Eromera/erfnet [Torch]
  • https://github.com/Eromera/erfnet_pytorch [PyTorch]
• RefineNet [https://arxiv.org/pdf/1611.06612.pdf] [2016]
  • https://github.com/guosheng/refinenet [MatConvNet]
• PSPNet [https://arxiv.org/pdf/1612.01105.pdf,https://hszhao.github.io/projects/pspnet/] [2017]
  • https://github.com/hszhao/PSPNet [Caffe]
  • https://github.com/ZijunDeng/pytorch-semantic-segmentation [PyTorch]
  • https://github.com/mitmul/chainer-pspnet [Chainer]
  • https://github.com/Vladkryvoruchko/PSPNet-Keras-tensorflow [Keras/Tensorflow]
  • https://github.com/pudae/tensorflow-pspnet [Tensorflow]
  • https://github.com/hellochick/PSPNet-tensorflow [Tensorflow]
  • https://github.com/hellochick/semantic-segmentation-tensorflow [Tensorflow]
  • https://github.com/qubvel/segmentation_models [Keras]
  • https://github.com/oandrienko/fast-semantic-segmentation [Tensorflow]
  • https://github.com/speedinghzl/pytorch-segmentation-toolbox [PyTorch]
  • https://github.com/youansheng/torchcv [PyTorch]
  • https://github.com/yassouali/pytorch_segmentation [PyTorch]
  • https://github.com/holyseven/PSPNet-TF-Reproduce [Tensorflow]
  • https://github.com/kazuto1011/pspnet-pytorch [PyTorch]
• DeconvNet [https://arxiv.org/pdf/1505.04366.pdf] [2015]
  • http://cvlab.postech.ac.kr/research/deconvnet/ [Caffe]
  • https://github.com/HyeonwooNoh/DeconvNet [Caffe]
  • https://github.com/fabianbormann/Tensorflow-DeconvNet-Segmentation [Tensorflow]
• FRRN [https://arxiv.org/pdf/1611.08323.pdf] [2016]
  • https://github.com/TobyPDE/FRRN [Lasagne]
• GCN [https://arxiv.org/pdf/1703.02719.pdf] [2017]
  • https://github.com/ZijunDeng/pytorch-semantic-segmentation [PyTorch]
  • https://github.com/ycszen/pytorch-seg [PyTorch]
  • https://github.com/yassouali/pytorch_segmentation [PyTorch]
• LRR [https://arxiv.org/pdf/1605.02264.pdf] [2016]
  • https://github.com/golnazghiasi/LRR [Matconvnet]
• DUC, HDC [https://arxiv.org/pdf/1702.08502.pdf] [2017]
  • https://github.com/ZijunDeng/pytorch-semantic-segmentation [PyTorch]
  • https://github.com/ycszen/pytorch-seg [PyTorch]
  • https://github.com/yassouali/pytorch_segmentation [PyTorch]
• MultiNet [https://arxiv.org/pdf/1612.07695.pdf] [2016]
  • https://github.com/MarvinTeichmann/MultiNet
  • https://github.com/MarvinTeichmann/KittiSeg
• Segaware [https://arxiv.org/pdf/1708.04607.pdf] [2017]
  • https://github.com/aharley/segaware [Caffe]
• Semantic Segmentation using Adversarial Networks [https://arxiv.org/pdf/1611.08408.pdf] [2016]
  • https://github.com/oyam/Semantic-Segmentation-using-Adversarial-Networks [Chainer]
• PixelDCN [https://arxiv.org/pdf/1705.06820.pdf] [2017]
  • https://github.com/HongyangGao/PixelDCN [Tensorflow]
• ShuffleSeg [https://arxiv.org/pdf/1803.03816.pdf] [2018]
  • https://github.com/MSiam/TFSegmentation [TensorFlow]
• AdaptSegNet [https://arxiv.org/pdf/1802.10349.pdf] [2018]
  • https://github.com/wasidennis/AdaptSegNet [PyTorch]
• TuSimple-DUC [https://arxiv.org/pdf/1702.08502.pdf] [2018]
  • https://github.com/TuSimple/TuSimple-DUC [MxNet]
• FPN [http://presentations.cocodataset.org/COCO17-Stuff-FAIR.pdf] [2017]
  • https://github.com/qubvel/segmentation_models [Keras]
• R2U-Net [https://arxiv.org/ftp/arxiv/papers/1802/1802.06955.pdf] [2018]
  • https://github.com/LeeJunHyun/Image_Segmentation#r2u-net [PyTorch]
• Attention U-Net [https://arxiv.org/pdf/1804.03999.pdf] [2018]
  • https://github.com/LeeJunHyun/Image_Segmentation#attention-u-net [PyTorch]
  • https://github.com/ozan-oktay/Attention-Gated-Networks [PyTorch]
• DANet [https://arxiv.org/pdf/1809.02983.pdf] [2018]
  • https://github.com/junfu1115/DANet [PyTorch]
• ShelfNet [https://arxiv.org/pdf/1811.11254.pdf] [2018]
  • https://github.com/juntang-zhuang/ShelfNet [PyTorch]
• LadderNet [https://arxiv.org/pdf/1810.07810.pdf] [2018]
  • https://github.com/juntang-zhuang/LadderNet [PyTorch]
• BiSeNet [https://arxiv.org/pdf/1808.00897.pdf] [2018]
  • https://github.com/ooooverflow/BiSeNet [PyTorch]
  • https://github.com/ycszen/TorchSeg [PyTorch]
  • https://github.com/zllrunning/face-parsing.PyTorch [PyTorch]
• ESPNet [https://arxiv.org/pdf/1803.06815.pdf] [2018]
  • https://github.com/sacmehta/ESPNet [PyTorch]
• DFN [https://arxiv.org/pdf/1804.09337.pdf] [2018]
  • https://github.com/ycszen/TorchSeg [PyTorch]
• CCNet [https://arxiv.org/pdf/1811.11721.pdf] [2018]
  • https://github.com/speedinghzl/CCNet [PyTorch]
• DenseASPP [http://openaccess.thecvf.com/content_cvpr_2018/papers/Yang_DenseASPP_for_Semantic_CVPR_2018_paper.pdf] [2018]
  • https://github.com/youansheng/torchcv [PyTorch]
• Fast-SCNN [https://arxiv.org/pdf/1902.04502.pdf] [2019]
  • https://github.com/DeepVoltaire/Fast-SCNN [PyTorch]
• HRNet [https://arxiv.org/pdf/1904.04514.pdf] [2019]
  • https://github.com/HRNet/HRNet-Semantic-Segmentation [PyTorch]
• PSANet [https://hszhao.github.io/papers/eccv18_psanet.pdf] [2018]
  • https://github.com/hszhao/PSANet [Caffe]
• UPSNet [https://arxiv.org/pdf/1901.03784.pdf] [2019]
  • https://github.com/uber-research/UPSNet [PyTorch]
• ConvCRF [https://arxiv.org/pdf/1805.04777.pdf] [2018]
  • https://github.com/MarvinTeichmann/ConvCRF [PyTorch]
• Multi-scale Guided Attention for Medical Image Segmentation [https://arxiv.org/pdf/1906.02849.pdf] [2019]
  • https://github.com/sinAshish/Multi-Scale-Attention [PyTorch]
• DFANet [https://arxiv.org/pdf/1904.02216.pdf] [2019]
  • https://github.com/huaifeng1993/DFANet [PyTorch]
• ExtremeC3Net [https://arxiv.org/pdf/1908.03093.pdf] [2019]
  • https://github.com/HYOJINPARK/ExtPortraitSeg [PyTorch]
• EncNet [https://arxiv.org/pdf/1803.08904.pdf] [2018]
  • https://github.com/zhanghang1989/PyTorch-Encoding [PyTorch]
• Unet++ [https://arxiv.org/pdf/1807.10165.pdf] [2018]
  • https://github.com/MrGiovanni/UNetPlusPlus [Keras]
  • https://github.com/4uiiurz1/pytorch-nested-unet [PyTorch]
• FastFCN [https://arxiv.org/pdf/1903.11816.pdf] [2019]
  • https://github.com/wuhuikai/FastFCN [PyTorch]
• PortraitNet [https://www.yongliangyang.net/docs/mobilePotrait_c&g19.pdf] [2019]
  • https://github.com/dong-x16/PortraitNet [PyTorch]
• GSCNN [https://arxiv.org/pdf/1907.05740.pdf] [2019]
  • https://github.com/nv-tlabs/gscnn [PyTorch]

Instance aware segmentation

• FCIS [https://arxiv.org/pdf/1611.07709.pdf]
  • https://github.com/msracver/FCIS [MxNet]
• MNC [https://arxiv.org/pdf/1512.04412.pdf]
  • https://github.com/daijifeng001/MNC [Caffe]
• DeepMask [https://arxiv.org/pdf/1506.06204.pdf]
  • https://github.com/facebookresearch/deepmask [Torch]
• SharpMask [https://arxiv.org/pdf/1603.08695.pdf]
  • https://github.com/facebookresearch/deepmask [Torch]
• Mask-RCNN [https://arxiv.org/pdf/1703.06870.pdf]
  • https://github.com/CharlesShang/FastMaskRCNN [Tensorflow]
  • https://github.com/jasjeetIM/Mask-RCNN [Caffe]
  • https://github.com/TuSimple/mx-maskrcnn [MxNet]
  • https://github.com/matterport/Mask_RCNN [Keras]
  • https://github.com/facebookresearch/maskrcnn-benchmark [PyTorch]
  • https://github.com/open-mmlab/mmdetection [PyTorch]
  • https://github.com/ZFTurbo/Keras-Mask-RCNN-for-Open-Images-2019-Instance-Segmentation [Keras]
• RIS [https://arxiv.org/pdf/1511.08250.pdf]
  • https://github.com/bernard24/RIS [Torch]
• FastMask [https://arxiv.org/pdf/1612.08843.pdf]
  • https://github.com/voidrank/FastMask [Caffe]
• BlitzNet [https://arxiv.org/pdf/1708.02813.pdf]
  • https://github.com/dvornikita/blitznet [Tensorflow]
• PANet [https://arxiv.org/pdf/1803.01534.pdf] [2018]
  • https://github.com/ShuLiu1993/PANet [Caffe]
• PAN [https://arxiv.org/pdf/1805.10180.pdf] [2018]
  • https://github.com/JaveyWang/Pyramid-Attention-Networks-pytorch [PyTorch]
• TernausNetV2 [https://arxiv.org/pdf/1806.00844.pdf] [2018]
  • https://github.com/ternaus/TernausNetV2 [PyTorch]
• MS R-CNN [https://arxiv.org/pdf/1903.00241.pdf] [2019]
  • https://github.com/zjhuang22/maskscoring_rcnn [PyTorch]
• AdaptIS [https://arxiv.org/pdf/1909.07829.pdf] [2019]
  • https://github.com/saic-vul/adaptis [MxNet][PyTorch]
• Pose2Seg [https://arxiv.org/pdf/1803.10683.pdf] [2019]
  • https://github.com/liruilong940607/Pose2Seg [PyTorch]
• YOLACT [https://arxiv.org/pdf/1904.02689.pdf] [2019]
  • https://github.com/dbolya/yolact [PyTorch]
• CenterMask [https://arxiv.org/pdf/1911.06667.pdf] [2019]
  • https://github.com/youngwanLEE/CenterMask [PyTorch]
  • https://github.com/youngwanLEE/centermask2 [PyTorch]
• InstaBoost [https://arxiv.org/pdf/1908.07801.pdf] [2019]
  • https://github.com/GothicAi/Instaboost [PyTorch]
• SOLO [https://arxiv.org/pdf/1912.04488.pdf] [2019]
  • https://github.com/WXinlong/SOLO [PyTorch]
• SOLOv2 [https://arxiv.org/pdf/2003.10152.pdf] [2020]
  • https://github.com/WXinlong/SOLO [PyTorch]
• D2Det [https://openaccess.thecvf.com/content_CVPR_2020/papers/Cao_D2Det_Towards_High_Quality_Object_Detection_and_Instance_Segmentation_CVPR_2020_paper.pdf] [2020] +https://github.com/JialeCao001/D2Det [PyTorch]

Weakly-supervised segmentation

• SEC [https://arxiv.org/pdf/1603.06098.pdf]
  • https://github.com/kolesman/SEC [Caffe]

RNN

• ReNet [https://arxiv.org/pdf/1505.00393.pdf]
  • https://github.com/fvisin/reseg [Lasagne]
• ReSeg [https://arxiv.org/pdf/1511.07053.pdf]
  • https://github.com/Wizaron/reseg-pytorch [PyTorch]
  • https://github.com/fvisin/reseg [Lasagne]
• RIS [https://arxiv.org/pdf/1511.08250.pdf]
  • https://github.com/bernard24/RIS [Torch]
• CRF-RNN [http://www.robots.ox.ac.uk/%7Eszheng/papers/CRFasRNN.pdf]
  • https://github.com/martinkersner/train-CRF-RNN [Caffe]
  • https://github.com/torrvision/crfasrnn [Caffe]
  • https://github.com/NP-coder/CLPS1520Project [Tensorflow]
  • https://github.com/renmengye/rec-attend-public [Tensorflow]
  • https://github.com/sadeepj/crfasrnn_keras [Keras]

GANS

• pix2pix [https://arxiv.org/pdf/1611.07004.pdf] [2018]
  • https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix [Pytorch]
  • https://github.com/affinelayer/pix2pix-tensorflow [Tensorflow]
• pix2pixHD [https://arxiv.org/pdf/1711.11585.pdf] [2018]
  • https://github.com/NVIDIA/pix2pixHD
• Probalistic Unet [https://arxiv.org/pdf/1806.05034.pdf] [2018]
  • https://github.com/SimonKohl/probabilistic_unet

Graphical Models (CRF, MRF)

• https://github.com/cvlab-epfl/densecrf
• http://vladlen.info/publications/efficient-inference-in-fully-connected-crfs-with-gaussian-edge-potentials/
• http://www.philkr.net/home/densecrf
• http://graphics.stanford.edu/projects/densecrf/
• https://github.com/amiltonwong/segmentation/blob/master/segmentation.ipynb
• https://github.com/jliemansifry/super-simple-semantic-segmentation
• http://users.cecs.anu.edu.au/~jdomke/JGMT/
• https://www.quora.com/How-can-one-train-and-test-conditional-random-field-CRF-in-Python-on-our-own-training-testing-dataset
• https://github.com/tpeng/python-crfsuite
• https://github.com/chokkan/crfsuite
• https://sites.google.com/site/zeppethefake/semantic-segmentation-crf-baseline
• https://github.com/lucasb-eyer/pydensecrf

Datasets:

• Stanford Background Dataset
• Sift Flow Dataset
• Barcelona Dataset
• Microsoft COCO dataset
• MSRC Dataset
• LITS Liver Tumor Segmentation Dataset
• KITTI
• Pascal Context
• Data from Games dataset
• Human parsing dataset
• Mapillary Vistas Dataset
• Microsoft AirSim
• MIT Scene Parsing Benchmark
• COCO 2017 Stuff Segmentation Challenge
• ADE20K Dataset
• INRIA Annotations for Graz-02
• Daimler dataset
• ISBI Challenge: Segmentation of neuronal structures in EM stacks
• INRIA Annotations for Graz-02 (IG02)
• Pratheepan Dataset
• Clothing Co-Parsing (CCP) Dataset
• ApolloScape
• UrbanMapper3D
• RoadDetector
• Cityscapes
• CamVid
• Inria Aerial Image Labeling

Benchmarks

• https://github.com/openseg-group/openseg.pytorch [PyTorch]
• https://github.com/open-mmlab/mmsegmentation [PyTorch]
• https://github.com/ZijunDeng/pytorch-semantic-segmentation [PyTorch]
• https://github.com/meetshah1995/pytorch-semseg [PyTorch]
• https://github.com/GeorgeSeif/Semantic-Segmentation-Suite [Tensorflow]
• https://github.com/MSiam/TFSegmentation [Tensorflow]
• https://github.com/CSAILVision/sceneparsing [Caffe+Matlab]
• https://github.com/BloodAxe/segmentation-networks-benchmark [PyTorch]
• https://github.com/warmspringwinds/pytorch-segmentation-detection [PyTorch]
• https://github.com/ycszen/TorchSeg [PyTorch]
• https://github.com/qubvel/segmentation_models [Keras]
• https://github.com/qubvel/segmentation_models.pytorch [PyTorch]
• https://github.com/Tramac/awesome-semantic-segmentation-pytorch [PyTorch]
• https://github.com/hszhao/semseg [PyTorch]
• https://github.com/yassouali/pytorch_segmentation [PyTorch]
• https://github.com/divamgupta/image-segmentation-keras [Keras]
• https://github.com/CSAILVision/semantic-segmentation-pytorch [PyTorch]
• https://github.com/thuyngch/Human-Segmentation-PyTorch [PyTorch]
• https://github.com/PaddlePaddle/PaddleSeg [PaddlePaddle]

Evaluation code

• [Cityscapes dataset] https://github.com/phillipi/pix2pix/tree/master/scripts/eval_cityscapes

Starter code

• https://github.com/mrgloom/keras-semantic-segmentation-example

Annotation Tools:

• https://github.com/AKSHAYUBHAT/ImageSegmentation
• https://github.com/kyamagu/js-segment-annotator
• https://github.com/CSAILVision/LabelMeAnnotationTool
• https://github.com/seanbell/opensurfaces-segmentation-ui
• https://github.com/lzx1413/labelImgPlus
• https://github.com/wkentaro/labelme
• https://github.com/labelbox/labelbox
• https://github.com/Deep-Magic/COCO-Style-Dataset-Generator-GUI
• https://github.com/Labelbox/Labelbox
• https://github.com/opencv/cvat
• https://github.com/saic-vul/fbrs_interactive_segmentation

Results:

• MSRC-21
• Cityscapes
• VOC2012
• https://paperswithcode.com/task/semantic-segmentation

Metrics

• https://github.com/martinkersner/py_img_seg_eval

Losses

• https://github.com/JunMa11/SegLoss
• http://www.cs.umanitoba.ca/~ywang/papers/isvc16.pdf
• https://arxiv.org/pdf/1705.08790.pdf
• https://arxiv.org/pdf/1707.03237.pdf
• http://www.bmva.org/bmvc/2013/Papers/paper0032/paper0032.pdf

Other lists

• https://paperswithcode.com/task/semantic-segmentation
• https://github.com/tangzhenyu/SemanticSegmentation_DL
• https://github.com/nightrome/really-awesome-semantic-segmentation
• https://github.com/JackieZhangdx/InstanceSegmentationList
• https://github.com/damminhtien/awesome-semantic-segmentation

Medical image segmentation:

• DIGITS

  • https://github.com/NVIDIA/DIGITS/tree/master/examples/medical-imaging

• U-Net: Convolutional Networks for Biomedical Image Segmentation

  • http://lmb.informatik.uni-freiburg.de/people/ronneber/u-net/
  • apache/mxnet#1514
  • https://github.com/orobix/retina-unet
  • https://github.com/fvisin/reseg
  • https://github.com/yulequan/melanoma-recognition
  • http://www.andrewjanowczyk.com/use-case-1-nuclei-segmentation/
  • https://github.com/junyanz/MCILBoost
  • https://github.com/imlab-uiip/lung-segmentation-2d
  • https://github.com/scottykwok/cervix-roi-segmentation-by-unet
  • https://github.com/WeidiXie/cell_counting_v2
  • https://github.com/yandexdataschool/YSDA_deeplearning17/blob/master/Seminar6/Seminar%206%20-%20segmentation.ipynb

• Cascaded-FCN

  • https://github.com/IBBM/Cascaded-FCN

• Keras

  • https://github.com/jocicmarko/ultrasound-nerve-segmentation
  • https://github.com/EdwardTyantov/ultrasound-nerve-segmentation
  • https://github.com/intact-project/ild-cnn
  • https://github.com/scottykwok/cervix-roi-segmentation-by-unet
  • https://github.com/lishen/end2end-all-conv

• Tensorflow

  • https://github.com/imatge-upc/liverseg-2017-nipsws
  • https://github.com/DLTK/DLTK/tree/master/examples/applications/MRBrainS13_tissue_segmentation

• Using Convolutional Neural Networks (CNN) for Semantic Segmentation of Breast Cancer Lesions (BRCA)

  • https://github.com/ecobost/cnn4brca

• Papers:

  • https://www2.warwick.ac.uk/fac/sci/dcs/people/research/csrkbb/tmi2016_ks.pdf
  • Sliding window approach
    • http://people.idsia.ch/~juergen/nips2012.pdf
  • https://github.com/albarqouni/Deep-Learning-for-Medical-Applications#segmentation

• Data:

  • https://luna16.grand-challenge.org/
  • https://camelyon16.grand-challenge.org/
  • https://github.com/beamandrew/medical-data

Satellite images segmentation

• https://github.com/mshivaprakash/sat-seg-thesis
• https://github.com/KGPML/Hyperspectral
• https://github.com/lopuhin/kaggle-dstl
• https://github.com/mitmul/ssai
• https://github.com/mitmul/ssai-cnn
• https://github.com/azavea/raster-vision
• https://github.com/nshaud/DeepNetsForEO
• https://github.com/trailbehind/DeepOSM
• https://github.com/mapbox/robosat
• https://github.com/datapink/robosat.pink

• Data:
  • https://github.com/RSIA-LIESMARS-WHU/RSOD-Dataset-
  • SpaceNet[https://spacenetchallenge.github.io/]
  • https://github.com/chrieke/awesome-satellite-imagery-datasets

Video segmentation

• https://github.com/shelhamer/clockwork-fcn
• https://github.com/JingchunCheng/Seg-with-SPN

Autonomous driving

• https://github.com/MarvinTeichmann/MultiNet
• https://github.com/MarvinTeichmann/KittiSeg
• https://github.com/vxy10/p5_VehicleDetection_Unet [Keras]
• https://github.com/ndrplz/self-driving-car
• https://github.com/mvirgo/MLND-Capstone
• https://github.com/zhujun98/semantic_segmentation/tree/master/fcn8s_road
• https://github.com/MaybeShewill-CV/lanenet-lane-detection

Other

Networks by framework (Older list)

• Keras

  • https://github.com/gakarak/FCN_MSCOCO_Food_Segmentation
  • https://github.com/abbypa/NNProject_DeepMask

• TensorFlow

  • https://github.com/warmspringwinds/tf-image-segmentation

• Caffe

  • https://github.com/xiaolonw/nips14_loc_seg_testonly
  • https://github.com/naibaf7/caffe_neural_tool

• torch

  • https://github.com/erogol/seg-torch
  • https://github.com/phillipi/pix2pix

• MXNet

  • https://github.com/itijyou/ademxapp

Papers and Code (Older list)

• Simultaneous detection and segmentation

  • http://www.eecs.berkeley.edu/Research/Projects/CS/vision/shape/sds/
  • https://github.com/bharath272/sds_eccv2014

• Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation

  • https://github.com/HyeonwooNoh/DecoupledNet

• Learning to Propose Objects

  • http://vladlen.info/publications/learning-to-propose-objects/
  • https://github.com/philkr/lpo

• Nonparametric Scene Parsing via Label Transfer

  • http://people.csail.mit.edu/celiu/LabelTransfer/code.html

• Other

  • https://github.com/cvjena/cn24
  • http://lmb.informatik.uni-freiburg.de/resources/software.php
  • https://github.com/NVIDIA/DIGITS/tree/master/examples/semantic-segmentation
  • http://jamie.shotton.org/work/code.html
  • https://github.com/amueller/textonboost

To look at

• keras-team/keras#6538
• https://github.com/warmspringwinds/tensorflow_notes
• https://github.com/kjw0612/awesome-deep-vision#semantic-segmentation
• https://github.com/desimone/segmentation-models
• https://github.com/nightrome/really-awesome-semantic-segmentation
• https://github.com/kjw0612/awesome-deep-vision#semantic-segmentation
• http://www.it-caesar.com/list-of-contemporary-semantic-segmentation-datasets/
• https://github.com/MichaelXin/Awesome-Caffe#23-image-segmentation
• https://github.com/warmspringwinds/pytorch-segmentation-detection
• https://github.com/neuropoly/axondeepseg
• https://github.com/petrochenko-pavel-a/segmentation_training_pipeline

Blog posts, other:

• https://handong1587.github.io/deep_learning/2015/10/09/segmentation.html
• http://www.andrewjanowczyk.com/efficient-pixel-wise-deep-learning-on-large-images/
• https://devblogs.nvidia.com/parallelforall/image-segmentation-using-digits-5/
• https://github.com/NVIDIA/DIGITS/tree/master/examples/binary-segmentation
• https://github.com/NVIDIA/DIGITS/tree/master/examples/semantic-segmentation
• http://blog.qure.ai/notes/semantic-segmentation-deep-learning-review
• https://medium.com/@barvinograd1/instance-embedding-instance-segmentation-without-proposals-31946a7c53e1