Light-Weight RefineNet for Real-Time Semantic Segmentation (pytorch)
- ShelfNet for Real-time Semantic Segmentation https://github.com/juntang-zhuang/ShelfNet
https://github.com/ZENGXH/DMM_Net
https://github.com/nv-tlabs/STEAL
全景分割相关资源大列表 https://github.com/Angzz/awesome-panoptic-segmentation
视觉分类/分割相关深度学习模型大列表 https://github.com/nerox8664/awesome-computer-vision-models
用于图像分割的各种Unet模型实现(PyTorch) https://github.com/bigmb/Unet-Segmentation-Pytorch-Nest-of-Unets
2019 语义分割指南 https://www.yanxishe.com/TextTranslation/1981
图像分割损失函数集 https://github.com/JunMa11/SegLoss
https://github.com/huochaitiantang/pytorch-deep-image-matting
Depth-wise Asymmetric Bottleneck for Real-time Semantic Segmentation (BMVC2019) https://github.com/Reagan1311/DABNet
TensorFlow model for training AdapNet++ for semantic segmentation http://deepscene.cs.uni-freiburg.de https://github.com/DeepSceneSeg/AdapNet-pp
深度学习语义分割相关资源大列表 https://github.com/tangzhenyu/SemanticSegmentation_DL
一文带你读懂 DeepMask（实例分割） https://www.yanxishe.com/TextTranslation/1591
PyTorch 语义分割 https://github.com/yassouali/pytorch_segmentation
Image Segmentation Using Deep Learning: A Survey https://www.arxiv-vanity.com/papers/2001.05566/ https://arxiv.org/abs/2001.05566
基于交互的实例分割学习 https://github.com/pathak22/seg-by-interaction
A higher performance pytorch implementation of DeepLab V3 Plus(DeepLab v3+) https://github.com/hualin95/Deeplab-v3plus
one-shot 分割 http://people.ee.ethz.ch/~cvlsegmentation/osvos/ https://github.com/kmaninis/OSVOS-PyTorch
Fast Video Object Segmentation by Reference-Guided Mask Propagation https://github.com/seoungwugoh/RGMP
CGNet: A Light-weight Context Guided Network for Semantic Segmentation https://github.com/wutianyiRosun/CGNet
Unified Perceptual Parsing for Scene Understanding https://github.com/CSAILVision/unifiedparsing
Segmenting Unknown 3D Objects from Real Depth Images using Mask R-CNN Trained on Synthetic Data https://github.com/BerkeleyAutomation/sd-maskrcnn
Predicting Future Instance Segmentation by Forecasting Convolutional Features https://github.com/facebookresearch/instpred
Code for paper in CVPR2019, 'Attentive Feedback Network for Boundary-aware Salient Object Detection', Mengyang Feng, Huchuan Lu and Errui Ding. https://github.com/ArcherFMY/AFNet
This is the code accompanying the ECCV 2018 publication on Superpixel Sampling Networks. https://github.com/NVlabs/ssn_superpixels
ENet - A Neural Net Architecture for real time Semantic Segmentation https://github.com/iArunava/ENet-Real-Time-Semantic-Segmentation
https://github.com/meng-tang/rloss
PyTorch implement of Deeply Supervised Salient Object Detection with Short Connection https://github.com/AceCoooool/DSS-pytorch
https://github.com/drogen120/OneshotTextureSegmentation https://github.com/LiamLYJ/scene_seg
convCRF快速分割后处理 https://arxiv.org/pdf/1805.04777.pdf https://github.com/MarvinTeichmann/ConvCRF 推广一下我们在domain adaptation for semantic segmentation的新工作。和目前众多基于adversarial learning的方法不同，我们基于简单而有效的self-training方法，在GTA2City, SYNTHIA2City, City2NTHU上达到SOTA, 并在CVPR WAD domain adaptation challenge斩获第一和第三 https://github.com/yzou2/cbst
Semantic Instance Segmentation with a Discriminative Loss Function https://github.com/Wizaron/instance-segmentation-pytorch
PyTorch-mask-x-rcnn - PyTorch implementation of the Mask-X-RCNN network https://github.com/skrish13/PyTorch-mask-x-rcnn
Open MMLab Detection Toolbox https://github.com/open-mmlab/mmdetection
Official implementation of "Minimizing Supervision for Free-space Segmentation" paper https://arxiv.org/abs/1711.05998 https://github.com/pfnet-research/superpixel-align
深度抠图(Keras/TensorFlow/OpenCV) https://github.com/foamliu/Deep-Image-Matting
Modified implementation for DVSNet based on Tensorflow https://github.com/XUSean0118/DVSNet
PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model https://arxiv.org/abs/1803.08225 https://github.com/octiapp/KerasPersonLab
photorealistic video-to-video translation https://github.com/NVIDIA/vid2vid
手机上实现的高速人像分割 https://github.com/lizhengwei1992/Fast_Portrait_Segmentation
CFUN: Combining Faster R-CNN and U-net Network for Efficient Whole Heart Segmentation https://github.com/Wuziyi616/CFUN
Maximum Classifier Discrepancy for Domain Adaptation https://github.com/mil-tokyo/MCD_DA
- Weakly- and Semi-Supervised Panoptic Segmentation https://github.com/qizhuli/Weakly-Supervised-Panoptic-Segmentation
Dual Attention Network for Scene Segmentation https://github.com/junfu1115/DANet
Keras 语义分割(预训练)模型库 https://github.com/qubvel/segmentation_models
ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation https://github.com/sacmehta/ESPNet
Tensorflow实现的DeepLab_V3 CNN 语义分割 https://github.com/sthalles/deeplab_v3
Geometry and Uncertainty in Deep Learning for Computer Vision https://github.com/alexgkendall/thesis
Multi-stream CNN based Video Semantic Segmentation for Automated Driving https://arxiv.org/abs/1901.02511
PyTorch implementation of DeepLabV3, trained on the Cityscapes dataset. https://github.com/fregu856/deeplabv3
基于 Mask R-CNN 的街景广告检测与模糊 https://github.com/WannaFIy/mask_AD
【DroneDeploy无人机图像分割基准】 https://github.com/dronedeploy/dd-ml-segmentation-benchmark
BodyPix(2.0)：TensorFlow.js 实现的浏览器里的实时人体图像分割 https://blog.tensorflow.org/2019/11/updated-bodypix-2.html https://storage.googleapis.com/tfjs-models/demos/body-pix/index.html
【语义分割训练/部署框架】'Bonnetal! - Bonnet and then some! Deep Learning Framework for various Image Recognition Tasks' https://github.com/PRBonn/bonnetal
A new codebase of Scene Graph Generation based on maskrcnn-benchmark. A Pytorch implementation of the CVPR 2020 Oral paper "Unbiased Scene Graph Generation from Biased Training" https://github.com/KaihuaTang/scene-graph-benchmark.pytorch
https://github.com/pymatting/pymatting
https://github.com/Yaoyi-Li/GCA-Matting
《Evolution of Image Segmentation using Deep Convolutional Neural Network: A Survey》 https://www.arxiv-vanity.com/papers/2001.04074/
《Learning a Spatio-Temporal Embedding for Video Instance Segmentation》 https://arxiv.org/abs/1912.08969
https://github.com/youngwanLEE/centermask2
https://github.com/zju3dv/snake/ https://arxiv.org/abs/2001.01629
【视频目标分割文献列表】 https://github.com/du0915/Video-Object-Segmentation-Paper-List
《UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation》 https://github.com/MrGiovanni/UNetPlusPlus
https://github.com/dbolya/yolact
时域一致性 https://github.com/irfanICMLL/ETC-Real-time-Per-frame-Semantic-video-segmentation
【PyTorch轻量实时语义分割模型】'Efficient-Segmentation-Networks - Lightweight models for real-time semantic segmentationon PyTorch (include SQNet, LinkNet, SegNet, UNet, ENet, ERFNet, EDANet, ESPNet, ESPNetv2, LEDNet, ESNet, FSSNet, CGNet, DABNet, Fast-SCNN, ContextNet, FPENet, etc.)' https://github.com/xiaoyufenfei/Efficient-Segmentation-Networks
【PyTorch语义分割模型集】’PyTorch for Semantic Segmentation - Support Fast_SCNN, HRNet, Deeplabv3_plus(xception, resnet, mobilenet), ContextNet, FPENet, DABNet, EdaNet, ENet, Espnetv2, RefineNet, UNet, DANet, HRNet, DFANet, HardNet, LedNet, OCNet, EncNet, DuNet, CGNet, CCNet, BiSeNet, PSPNet, ICNet, FCN, deeplab)' https://github.com/LikeLy-Journey/SegmenTron
道路图像(街景)快速语义分割 https://github.com/lxtGH/Fast_Seg
CARAFE: Content-Aware ReAssembly of FEatures https://github.com/XiaLiPKU/CARAFE
https://github.com/youngwanLEE/CenterMask
implement for paper: "RDSNet: A New Deep Architecture for Reciprocal Object Detection and Instance Segmentation" https://github.com/wangsr126/RDSNet
Real-time Localized Style Transfer with Semantic Segmentation https://github.com/IssamLaradji/CBStyling
(NeurIPS2019) Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation https://github.com/RogerZhangzz/CAG_UDA
Bayesian Adaptive Superpixel Segmentation https://github.com/BGU-CS-VIL/BASS
Implementation of Deep Complex UNet Using PyTorch https://github.com/sweetcocoa/DeepComplexUNetPyTorch
Natural Image Matting via Guided Contextual Attention https://github.com/Yaoyi-Li/GCA-Matting
Zero-Shot Semantic Segmentation https://arxiv.org/pdf/1906.00817.pdf
https://github.com/valeoai/ZS3
Object-Contextual Representations for Semantic Segmentation in PyTorch https://github.com/rosinality/ocr-pytorch
https://github.com/TAMU-VITA/FasterSeg
Segmenting Objects by Locations https://github.com/Epiphqny/SOLO
[CVPR 2019, Oral] "Collaborative Global-Local Networks for Memory-Efficient Segmentation of Ultra-High Resolution Images" https://github.com/TAMU-VITA/GLNet
Efficient Segmentation: Learning Downsampling Near Semantic Boundaries https://github.com/dmitrii-marin/adaptive-sampling
The code is unofficial version for TensorMask: A Foundation for Dense Object Segmentation. https://github.com/CaoWGG/TensorMask
Unofficial implementation of Fast-SCNN: Fast Semantic Segmentation Network https://github.com/DeepVoltaire/Fast-SCNN
Implementation of NeurIPS 2019 paper "Weakly Supervised Instance Segmentation using the Bounding Box Tightness Prior" https://github.com/chengchunhsu/WSIS_BBTP
Code for Universal Semi-Supervised Semantic Segmentation models paper accepted in ICCV 2019 https://github.com/tarun005/USSS_ICCV19
The Pytorch implementation of "Location-aware Upsampling for Semantic Segmentation" (LaU) https://github.com/HolmesShuan/Location-aware-Upsampling-for-Semantic-Segmentation
【(PyTorch)实例分割/对象检测算法快速模块化参考实现】’Rotated Mask R-CNN - Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.' https://github.com/mrlooi/rotated_maskrcnn
NAS-Unet: Neural Architecture Search for Medical Image Segmentation https://github.com/tianbaochou/NasUnet
UNet++: A Nested U-Net Architecture for Medical Image Segmentation implemented in PyTorch. https://github.com/4uiiurz1/pytorch-nested-unet
Video Object Segmentation using Space-Time Memory Networks https://github.com/seoungwugoh/stm
Fully Convolutional HarDNet for Segmentation in Pytorch https://github.com/PingoLH/FCHarDNet
Code for the paper "Pose2Seg: Detection Free Human Instance Segmentation" @ CVPR2019. https://github.com/erezposner/Pose2Seg
SqueezeNAS: Fast Neural Architecture Search for Faster Semantic Segmentation https://github.com/ashaw596/squeezenas
Pytorch Code release for our NeurIPS paper "Multi-source Domain Adaptation for Semantic Segmentation" https://github.com/Luodian/MADAN
Criss-Cross Attention for Semantic Segmentation in pure Pytorch with a faster and more precise implementation. https://github.com/Serge-weihao/CCNet-Pure-Pytorch
Code for NeurIPS 2019 paper Emergence of Object Segmentation in Perturbed Generative Models https://github.com/adambielski/perturbed-seg
The Best of Both Modes: Separately Leveraging RGB and Depth for Unseen Object Instance Segmentation https://github.com/chrisdxie/uois
This repository is for Asymmetric Non-local Neural Networks for Semantic Segmentation (to appear in ICCV 2019) https://github.com/MendelXu/ANN
Official PyTorch implementation of "Unsupervised Microvascular Image Segmentation Using an Active Contours Mimicking Neural Network" https://github.com/shirgur/UMIS
This is the code for GMIS, which is published on ECCV 2018 as "Pixel Derivation and Graph Merge for Instance Segmentation" https://github.com/xck36/GMIS
Anchor Diffusion for Unsupervised Video Object Segmentation https://github.com/yz93/anchor-diff-VOS
Detectron with VoVNet(CVPRW'19) backbone networks https://github.com/vov-net/VoVNet-Detectron
A Cross-Season Correspondence Dataset for Robust Semantic Segmentation https://github.com/maunzzz/cross-season-segmentation
BCDU-Net : Medical Image Segmentation https://github.com/rezazad68/BCDU-Net
SegSort: Segmentation by Discriminative Sorting of Segments https://github.com/jyhjinghwang/SegSort
code for paper Boundary and Entropy-driven Adversarial Learning for Fundus Image Segmentation https://github.com/EmmaW8/BEAL
The pytorch implementation of self-supervised scale equivariant network for weakly supervised semantic segmentation. https://github.com/YudeWang/SSENet-pytorch
https://github.com/yu4u/kaggle-open-images-2019-instance-segmentation
https://github.com/xieenze/PolarMask
RANet: Ranking Attention Network for Fast Video Object Segmentation (VOS), ICCV2019 https://github.com/Storife/RANet
前背景分割(抠图)相关文献与资源列表 https://github.com/murari023/awesome-background-subtraction
TensorMask：一种新的密集滑动窗口实例分割技术 https://research.fb.com/publications/tensormask-a-foundation-for-dense-object-segmentation/
a tensorflow version for DSRG (Weakly-Supervised Semantic Segmentation Network with Deep Seeded Region Growing) https://github.com/xtudbxk/DSRG-tensorflow
https://github.com/eti-p-doray/unet-gan-matting
Unsupervised Image Segmentation by Backpropagation https://github.com/kanezaki/pytorch-unsupervised-segmentation
用Unet/Keras/TensorFlow.js实现的图片去背景 https://ldenoue.github.io/keras-unet/ https://github.com/ldenoue/keras-unet
(PyTorch)U-Net, R2U-Net, Attention U-Net, Attention R2U-Net图像分割 https://github.com/LeeJunHyun/Image_Segmentation
PyTorch语义分割(DeepLabV3+, UNet, etc.) https://github.com/nyoki-mtl/pytorch-segmentation
Pytorch code for semantic segmentation using ERFNet https://github.com/Eromera/erfnet_pytorch
(ECCV 2018)COCO2018全景分割比赛第三名方案 https://github.com/LaoYang1994/PanopticSegmentation
语义分割、实例分割、全景分割和视频分割的论文和基准列表 https://github.com/wutianyiRosun/Segmentation.X
Generalized Intersection over Union - PyTorch Faster/Mask R-CNN https://github.com/generalized-iou/Detectron.pytorch
FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation https://github.com/wuhuikai/FastFCN
Semantic Segmentation for Line Drawing Vectorization Using Neural Networks https://github.com/byungsook/vectornet
Bonnet: An Open-Source Training and Deployment Framework for Semantic Segmentation in Robotics. https://github.com/PRBonn/bonnet
实时语义分割模型集锦 https://github.com/xiaoyufenfei/Real-Time-Semantic-Segmentation
Tensorflow implementation of "Semantic Instance Segmentation with a Discriminative Loss Function" https://github.com/hq-jiang/instance-segmentation-with-discriminative-loss-tensorflow
LEDNet: A Lightweight Encoder-Decoder Network for Real-time Semantic Segmentation https://github.com/xiaoyufenfei/LEDNet A pytorch implementation of BDL. If you use this code in your research please consider citing https://github.com/liyunsheng13/BDL
Instance Segmentation by Deep Coloring https://github.com/kulikovv/DeepColoring
A PyTorch Implementation of Fast-SCNN: Fast Semantic Segmentation Network https://github.com/Tramac/Fast-SCNN-pytorch
reimpliment of DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation https://github.com/huaifeng1993/DFANet
The code for Expectation-Maximization Attention Networks for Semantic Segmentation (ICCV'2019 Oral) https://github.com/XiaLiPKU/EMANet
A PyTorch implementation of PointRend: Image Segmentation as Rendering https://github.com/zsef123/PointRend-PyTorch
"Context-aware Image Matting for Simultaneous Foreground and Alpha Estimation" https://github.com/hqqxyy/Context-Aware-Matting
https://github.com/shelhamer/revolver
Depth-wise Asymmetric Bottleneck for Real-time Semantic Segmentation (BMVC2019) https://github.com/Reagan1311/DABNet
Implementation of Pyramid Attention Networks for Semantic Segmentation. https://github.com/JaveyWang/Pyramid-Attention-Networks-pytorch
Pytorch implementation of GCN architecture for semantic segmentation https://github.com/SConsul/Global_Convolutional_Network
Learning Superpixels with Segmentation-Aware Affinity Loss https://github.com/wctu/SEAL
High-resolution representation learning (HRNets) for Semantic Segmentation https://github.com/HRNet/HRNet-Semantic-Segmentation
PyTorch implementation of PSPNet https://github.com/kazuto1011/pspnet-pytorch
https://github.com/sydney0zq/PTSNet
Fast, high accuracy video segmentation framework (CVPR 2019 oral) http://www.samvitjain.com/accel/
https://github.com/SamvitJ/Accel
https://github.com/mapillary/seamseg/
Pytorch Implementation -- All about Structure: Adapting Structural Information across Domains for Boosting Semantic Segmentation, CVPR 2019 https://github.com/a514514772/DISE-Domain-Invariant-Structure-Extraction
(TensorFlow 2.0)U-Net图像分割教程 https://www.tensorflow.org/beta/tutorials/images/segmentation
Grape detection, segmentation and tracking using deep neural networks and three-dimensional association https://github.com/thsant/wgisd
Gated-SCNN: Gated Shape CNNs for Semantic Segmentation https://github.com/nv-tlabs/GSCNN https://arxiv.org/abs/1907.05740
https://github.com/foamliu/Look-Into-Person
https://github.com/mateuszbuda/brain-segmentation-pytorch
https://github.com/NVIDIA/semantic-segmentation
STEAL - Learning Semantic Boundaries from Noisy Annotations https://nv-tlabs.github.io/STEAL/
https://github.com/nv-tlabs/STEAL
PyTorch implementation of the paper "A Generative Appearance Model for End-to-End Video Object Segmentation".
https://github.com/joakimjohnander/agame-vos
图像分割/显著性检测数据集列表 https://github.com/lartpang/awesome-segmentation-saliency-dataset
Colab)宠物图片分割实例 https://colab.research.google.com/drive/1EJKlMKrdlZ5BctIWlk3TrXJfE7dzpiaH
paper:Budget-aware Semi-Supervised Semantic and Instance Segmentation https://arxiv.org/abs/1905.05880
Learning to Reconstruct People in Clothing from a Single RGB Camera. https://github.com/thmoa/octopus
https://github.com/YBIGTA/pytorch-hair-segmentation
Virtual KITTI 3D Dataset for Semantic Segmentation https://github.com/VisualComputingInstitute/vkitti3D-dataset
PyTorch Semantic Segmentation https://github.com/hszhao/semseg
Tensorflow implementation of our paper: Few-shot 3D Multi-modal Medical Image Segmentation using Generative Adversarial Learning https://github.com/arnab39/FewShot_GAN-Unet3D
(PyTorch)语义分割参考实现 https://github.com/lingtengqiu/Deeperlab-pytorch
https://github.com/youtubevos/MaskTrackRCNN
图像分割文献/代码集锦(语义分割、2D医学分割、3D医学分割、实例分割、全景分割) https://github.com/xiaoketongxue/CV-News
code used for CVPR2019 oral "Collaborative Global-Local Networks for Memory-Efficient Segmentation of Ultra-High Resolution Images" https://github.com/chenwydj/ultra_high_resolution_segmentation
全景分割相关资源大列表 https://github.com/Angzz/awesome-panoptic-segmentation
PyTorch实现的图像分割与预训练模型 https://github.com/qubvel/segmentation_models.pytorch
医学图像分割框架 https://github.com/MIC-DKFZ/nnUNet
https://github.com/huuuuusy/Mask-RCNN-Shiny
https://github.com/nizhib/portrait-demo
Dense Relation Network: Learning Consistent and Context-Aware Representation For Semantic Image Segmentation. Modification of DRN source code https://github.com/tonysy/DRN-MXNet
A Probabilistic U-Net for segmentation of ambiguous images implemented in PyTorch https://github.com/stefanknegt/Probabilistic-Unet-Pytorch
In Defense of Pre-trained ImageNet Architectures for Real-time Semantic Segmentation of Road-driving Images https://github.com/orsic/swiftnet
FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation https://github.com/wuhuikai/FastFCN
OpenCV深度学习时装图片降噪/分割 https://github.com/anish9/Fashion-AI-segmentation
https://github.com/dbolya/yolact
Analysis of Hand Segmentation in the Wild https://github.com/aurooj/Hand-Segmentation-in-the-Wild
ICNet and PSPNet-50 in Tensorflow for real-time semantic segmentation https://github.com/oandrienko/fast-semantic-segmentation
Tree-structured Kronecker Convolutional Network for Semantic Segmentation [Accepted by ICME 2019] https://github.com/wutianyiRosun/TKCN
nnU-Net is a framework designed for medical image segmentation. Given a new dataset (that includes training cases) nnU-Net will automatically take care of the entire experimental pipeline. Unlike other segmentation methods published recently, nnU-Net does not use complicated architectural modifications and instead revolves around the popular U-Net architecture. Still, nnU-Net outperforms many other methods and has been shown to produce segmentations that are on par with or even exceed the state-of-the art across six well-known medical segmentation challenges. https://github.com/MIC-DKFZ/nnUNet
RVOS: End-to-End Recurrent Network for Video Object Segmentation https://imatge-upc.github.io/rvos/ https://github.com/imatge-upc/rvos
https://github.com/wenz116/TransferSeg
https://github.com/bethgelab/siamese-mask-rcnn
https://github.com/jfzhang95/DeepGrabCut-PyTorch
https://github.com/linjieyangsc/video_seg
Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation, CVPR 2018
https://github.com/jiwoon-ahn/psa
基于PyTorch 1.0的高性能图像检测/分割实现，比Detectron快2倍 https://github.com/facebookresearch/maskrcnn-benchmark
DeepLab v3+ model in PyTorch. Support different backbones. https://github.com/jfzhang95/pytorch-deeplab-xception
(PyTorch)快速、模块化语义分割模型参考实现 https://github.com/ycszen/TorchSeg
PyTorch 实现的PSPNet、DeepLabV3、DenseASPP等深度学习语义分割 https://github.com/donnyyou/torchcv-seg
用Python/scikit-image实现图像分割 https://towardsdatascience.com/image-segmentation-using-pythons-scikit-image-module-533a61ecc980
DeepMask的PyTorch实现 https://github.com/foolwood/deepmask-pytorch
DeepLabv3.pytorch - PyTorch implementation of DeepLabv3 https://github.com/chenxi116/DeepLabv3.pytorch
https://blog.stratospark.com/generating-synthetic-data-image-segmentation-unity-pytorch-fastai.html
弱监督语义分割先进方法资源列表 https://github.com/JackieZhangdx/WeakSupervisedSegmentationList
DeepLabv3plus Semantic Segmentation in Pytorch - deeplabv3+ supporting ResNet(79.155%) and Xception(79.945%) https://github.com/YudeWang/deeplabv3plus-pytorch
https://github.com/aim-uofa/AdelaiDet/
SOLOv2的非官方PyTorch实现 https://github.com/Epiphqny/SOLOv2
2020图像分割纵览 https://neptune.ai/blog/image-segmentation-in-2020
Foodly 开发的配菜机器人：通过深度图像识别挑选便当配菜完成拼盘，可准确识别每块炸肉边界 https://developers-jp.googleblog.com/2020/04/tensorflow-foodly.html
Boosting Semantic Human Matting with Coarse Annotations https://www.arxiv-vanity.com/papers/2004.04955/
https://neptune.ai/blog/image-segmentation-tips-and-tricks-from-kaggle-competitions
https://github.com/feipan664/IntraDA
Footprints and Free Space from a Single Color Image https://github.com/nianticlabs/footprints
Correlating Edge, Pose with Parsing https://github.com/ziwei-zh/CorrPM
https://github.com/NathanUA/U-2-Net
Improving Semantic Segmentation via Self-Training https://www.arxiv-vanity.com/papers/2004.14960/
【图像标签单级语义分割】’Single-Stage Semantic Segmentation from Image Labels (CVPR 2020)' https://github.com/visinf/1-stage-wseg
【图像分割2020最新进展】《Image segmentation in 2020》 https://towardsdatascience.com/image-segmentation-in-2020-756b77fa88fc
【PixelLib：图像语义分割/实例分割库】’PixelLib - a library for performing segmentation of images' https://github.com/ayoolaolafenwa/PixelLib https://medium.com/@olafenwaayoola/image-segmentation-with-six-lines-0f-code-acb870a462e8
【EfficientPS：高性能全景分割】《EfficientPS: Efficient Panoptic Segmentation》 https://github.com/DeepSceneSeg/EfficientPS
【Google Coral人体分割模块】 https://github.com/google-coral/project-bodypix
【参考图像分割文献/资源列表】 https://github.com/MarkMoHR/Awesome-Referring-Image-Segmentation
https://github.com/facebookresearch/detectron2/tree/master/projects/PointRend
【多尺度Attention语义分割】 https://developer.nvidia.com/blog/using-multi-scale-attention-for-semantic-segmentation/
https://github.com/researchmm/TracKit
'DeepLabv3Plus-Pytorch - DeepLabV3 and DeepLabV3+ with MobileNetv2 and ResNet backbones for Pytorch.' https://github.com/VainF/DeepLabV3Plus-Pytorch
https://github.com/carrierlxk/GraphMemVOS https://www.arxiv-vanity.com/papers/2007.07020/
https://github.com/openseg-group/openseg.pytorch
《基于深度学习的图像分割在高德的实践》 https://yqh.aliyun.com/detail/15920?utm_content=g_1000154176
【计图语义分割模型库】'segmentation-jittor - jittor segmentation lib' https://github.com/Jittor/segmentation-jittor
【用Keras实现深度学习中的一些语义分割模型】 https://github.com/BBuf/Keras-Semantic-Segmentation
《Unsupervised Learning of Image Segmentation Based on Differentiable Feature Clustering》 https://github.com/kanezaki/pytorch-unsupervised-segmentation-tip/
https://github.com/z-x-yang/CFBI https://www.arxiv-vanity.com/papers/2003.08333/
https://github.com/JialeCao001/SipMask
https://github.com/plotly/dash-sample-apps/tree/master/apps/dash-image-segmentation
Attention-Guided Hierarchical Structure Aggregation for Image Matting https://github.com/wukaoliu/CVPR2020-HAttMatting
https://github.com/rezazad68/fewshot-segmentation
HANet is an add-on module for urban-scene segmentation to exploit the structural priors existing in urban-scene https://github.com/shachoi/HANet
code for CVPR 2020 paper: Learning Video Object Segmentation from Unlabeled Videos https://github.com/carrierlxk/MuG
Learning Dynamic Routing for Semantic Segmentation https://github.com/yanwei-li/DynamicRouting
YOLACT: Real-time Instance Segmentation on the FCOS detector (without bbox cropping), achives 35.2mAP on coco val https://github.com/Epiphqny/Yolact_fcos
Unofficial implementation for SOLO instance segmentation https://github.com/Liusifei/SOLO_beta
[CVPR‘20] SpixelFCN: Superpixel Segmentation with Fully Convolutional Network https://github.com/fuy34/superpixel_fcn
Official repository for the paper F, B, Alpha Matting. https://github.com/MarcoForte/FBA_Matting
Conditional Convolutions for Instance Segmentation, achives 37.1mAP on coco val https://github.com/Epiphqny/CondInst
BUDA: Boundless Unsupervised Domain Adaptation in Semantic Segmentation https://github.com/valeoai/BUDA
Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation, CVPR 2020 (Oral) https://github.com/YudeWang/SEAM
Learning to Segment the Tail https://github.com/JoyHuYY1412/LST_LVIS
Code accompanying the paper Learning Fast and Robust Target Models for Video Object Segmentation https://github.com/andr345/frtm-vos
a transductive approach for video object segmentation https://github.com/microsoft/transductive-vos.pytorch
D3S - Discriminative Single Shot Segmentation Tracker https://github.com/alanlukezic/d3s
An Official Repo of CVPR '20 "MSeg: A Composite Dataset for Multi-Domain Segmentation" https://github.com/mseg-dataset/mseg-api
Complete-IoU (CIoU) Loss and Cluster-NMS for Object Detection and Instance Segmentation (YOLACT) https://github.com/Zzh-tju/CIoU
[CVPR2020] CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement https://github.com/hkchengrex/CascadePSP
Semi-supevised Semantic Segmentation with High- and Low-level Consistency https://github.com/sud0301/semisup-semseg
Temporally Distributed Networks for Fast Video Semantic Segmentation https://github.com/feinanshan/TDNet
Super-BPD: Super Boundary-to-Pixel Direction for Fast Image Segmentation (CVPR 2020) https://github.com/JianqiangWan/Super-BPD
A Late Fusion CNN for Digital Matting https://github.com/yunkezhang/FusionMatting
Coarse to Fine Vertebrae Localization and Segmentation with SpatialConfiguration-Net and U-Net https://github.com/christianpayer/MedicalDataAugmentationTool-VerSe
Fast Soft Color Segmentation https://github.com/pfnet-research/FSCS
An Official Repo of CVPR '20 "MSeg: A Composite Dataset for Multi-Domain Segmentation" https://github.com/mseg-dataset/mseg-semantic
This is Pytorch re-implementation of our CVPR 2020 paper "Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation" https://github.com/bowenc0221/panoptic-deeplab
This code is an official implementation of "D2Det: Towards High Quality Object Detection and Instance Segmentation (CVPR2020)" https://github.com/JialeCao001/D2Det
Official pytorch implementation for "Video Panoptic Segmentation" (CVPR 2020 Oral) https://github.com/mcahny/vps
Learning Saliency Propagation for Semi-supervised Instance Segmentation https://github.com/ucbdrive/ShapeProp
Instance Shadow Detection (CVPR 2020) https://github.com/stevewongv/InstanceShadowDetection
Official re-implementation of the Calibrated Adversarial Refinement model described in the paper "Calibrated Adversarial Refinement for Multimodal Semantic Segmentation" https://github.com/EliasKassapis/CARMSS
Getting to 99% Accuracy in Interactive Segmentation and Interactive Training and Architecture for Deep Object Selection
https://github.com/MarcoForte/DeepInteractiveSegmentation
SOLO and SOLOv2 for instance segmentation. https://github.com/WXinlong/SOLO
Unofficial tensorflow implementation of real-time scene image segmentation model "BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation" https://github.com/MaybeShewill-CV/bisenetv2-tensorflow
Real-Time Panoptic Segmentation from Dense Detections https://github.com/TRI-ML/realtime_panoptic
PointTrack(ECCV2020 ORAL): Segment as Points for Efficient Online Multi-Object Tracking and Segmentation https://github.com/detectRecog/PointTrack
Semi-Supervised Semantic Image Segmentation With Self-Correcting Networks. Mostafa S. Ibrahim, Arash Vahdat, Mani Ranjbar, William G. Macready. IEEE Computer Vision and Pattern Recognition 2020 https://github.com/mostafa-saad/segment-correction-net
Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic Segmentation https://github.com/SHI-Labs/Unsupervised-Domain-Adaptation-with-Differential-Treatment
Official repository for Hierarchical Opacity Propagation for Image Matting https://github.com/Yaoyi-Li/HOP-Matting
This is the pytorch implementation of the CVPR2020 paper "Memory aggregation networks for efficient interactive video object segmentation". https://github.com/lightas/CVPR2020_MANet
Semi-supervised semantic segmentation needs strong, varied perturbations https://github.com/Britefury/cutmix-semisup-seg
Learning Integral Objects with Intra-Class Discriminator for Weakly-Supervised Semantic Segmentation https://github.com/js-fan/ICD
https://github.com/WaterKnight1998/SemTorch
https://github.com/CaoWGG/CenterNet-CondInst
Forest R-CNN: Large-Vocabulary Long-Tailed Object Detection and Instance Segmentation (ACM MM 2020) https://github.com/JialianW/Forest_RCNN
https://github.com/Yang-Bob/PMMs
https://github.com/Jia-Research-Lab/PFENet
https://github.com/Yang-Bob/PMMs
Code for our ACMMM2020 paper "Context-aware Feature Generation for Zero-shot Semantic Segmentation". https://github.com/bcmi/CaGNet-Zero-Shot-Semantic-Segmentation
Fourier Domain Adaptation for Semantic Segmentation https://github.com/YanchaoYang/FDA
视频实例分割文献/代码/数据集大列表 https://github.com/jiawen9611/Awesome-Video-Instance-Segmentation
PyTorch实现的MobileNetV3实时语义分割 https://github.com/ekzhang/fastseg
【卫星图像城市道路提取】'City-scale Road Extraction from Satellite Imagery - Road network extraction from satellite imagery, with speed and travel time estimates' https://github.com/avanetten/cresi
【AniSeg：漫画人物分割】 https://github.com/jerryli27/AniSeg
Keras实现的多种语义分割损失函数 https://github.com/shruti-jadon/Semantic-Segmentation-Loss-Functions
半监督视频目标分割(VOS)文献/实现列表 https://github.com/cheng321284/VOS-Paper-List
High-Resolution Deep Image Matting https://arxiv.org/abs/2009.06613
SemTorch：PyTorch深度学习图像分割库 https://github.com/WaterKnight1998/SemTorch
ECCV 2020实例级识别Workshop上Google成果介绍，包括新的DELG模型，新资源以及开源库，以及两个挑战的地标识别和检索任务 https://ai.googleblog.com/2020/09/advancing-instance-level-recognition.html
https://github.com/hoya012/semantic-segmentation-tutorial-pytorch
Deep Image Compositing https://arxiv.org/abs/2011.02146
Is a Green Screen Really Necessary for Real-Time Human Matting https://github.com/ZHKKKe/MODNet
BoxInst: High-Performance Instance Segmentation with Box Annotations https://github.com/aim-uofa/AdelaiDet/
https://github.com/dvl-tum/e-osvos
ViP-DeepLab: Learning Visual Perception with Depth-aware Video Panoptic Segmentation https://github.com/joe-siyuan-qiao/ViP-DeepLab
Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation https://arxiv.org/abs/2012.07177
基于CondInst的动画角色实例分割 https://github.com/zymk9/Yet-Another-Anime-Segmenter
Real-Time High-Resolution Background Matting https://arxiv.org/abs/2012.07810
https://github.com/haotian-liu/yolact_edge
HyperSeg: Patch-wise Hypernetwork for Real-time Semantic Segmentation https://arxiv.org/abs/2012.11582
Meticulous Object Segmentation https://github.com/Chenglin-Yang/MOS_Meticulous-Object-Segmentation
RGBD semantic segmentation：RGBD语义分割文献/资源列表 https://github.com/Yangzhangcst/RGBD-semantic-segmentation
https://github.com/chwilms/superpixelRefinement
Dynamic Graph Message Passing Networks (DGMN) in PyTorch 1.0 https://github.com/lzrobots/dgmn
Pytorch实现的2D/3D医学图像分割 https://github.com/MontaEllis/Pytorch-Medical-Segmentation
Segmenting Transparent Object in the Wild with Transformer https://arxiv.org/abs/2101.08461
SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation https://arxiv.org/abs/2101.08833
Exploring Cross-Image Pixel Contrast for Semantic Segmentation https://github.com/tfzhou/ContrastiveSeg
Occluded Video Instance Segmentation https://arxiv.org/abs/2102.01558
Recurrent U-Net for Resource Constraint Segmentation https://github.com/kcyu2014/recurrent-unet
Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentation https://github.com/JDAI-CV/FADA
Data and code for ECCV2020 paper 'Segmenting Transparent Objects in the Wild' https://github.com/xieenze/Segment_Transparent_Objects
Content-Consistent Matching for Domain Adaptive Semantic Segmentation https://github.com/Solacex/CCM
Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation https://github.com/GuoleiSun/MCIS_wsss
FDA: Fourier Domain Adaptation for Semantic Segmentation. https://github.com/YanchaoYang/FDA
ViewAL: Active Learning with Viewpoint Entropy for Semantic Segmentation https://github.com/nihalsid/ViewAL
https://github.com/shiyinzhang/Inside-Outside-Guidance
This repository contains the official implementation of the paper "STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos" https://github.com/sabarim/STEm-Seg
Reliability Does Matter: An End-to-End Weakly Supervised Semantic Segmentation Approach https://github.com/zbf1991/RRM
Code for “Disentangled Non-local Neural Networks” https://github.com/yinmh17/DNL-Semantic-Segmentation
SC-CAM: Weakly-Supervised Semantic Segmentation via Sub-category Exploration (CVPR 2020) https://github.com/Juliachang/SC-CAM
Official code for "Object counting and instance segmentation with image-level supervision", in CVPR 2019 and TPAMI 2020 https://github.com/GuoleiSun/CountSeg
Official Implementation of Part-aware Prototype Network for Few-shot Semantic Segmentation https://github.com/Xiangyi1996/PPNet-PyTorch
Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimation https://github.com/FangyunWei/PointSetAnchor
https://github.com/JialeCao001/D2Det-mmdet2.1
Offical code base for the ECCV oral paper "Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation" https://github.com/YingdaXia/SynthCP
Code for ICASSP 2020 paper ‘UNet 3+: A full-scale connected unet for medical image segmentation’ https://github.com/ZJUGiveLab/UNet-Version
A simple consistency training framework for semi-supervised image semantic segmentation https://github.com/googleinterns/wss
ACFNet: Attentional Class Feature Network for Semantic Segmentation.(ICCV2019) https://github.com/zrl4836/ACFNet
Semi Supervised Learning for Medical Image Segmentation, a collection of literature reviews and code implementations. https://github.com/HiLab-git/SSL4MIS
[ECCV'20] Self-supervision with Superpixels: Training Few-shot Medical Image Segmentation without Annotation (code&data-processing pipeline) https://github.com/cheng-01037/Self-supervised-Fewshot-Medical-Image-Segmentation
Intra-class Feature Variation Distillation for Semantic Segmentation https://github.com/YukangWang/IFVD
Making a Case for 3D Convolutions for Object Segmentation in Videos https://github.com/sabarim/3DC-Seg
ViP-DeepLab: Learning Visual Perception with Depth-aware Video Panoptic Segmentation https://github.com/joe-siyuan-qiao/ViP-DeepLab
Real-Time High-Resolution Background Matting https://github.com/PeterL1n/BackgroundMattingV2
A framework for Medical Image Segmentation with Convolutional Neural Networks and Deep Learning https://github.com/frankkramer-lab/MIScnn
This repository includes the official project of Mask Guided (MG) Matting, presented in our paper: Mask Guided Matting via Progressive Refinement Network https://github.com/yucornetto/MGMatting
An implementation of our work "Three Ways to Improve Semantic Segmentation with Self-Supervised Depth Estimation" https://github.com/lhoyer/improving_segmentation_with_selfsupervised_depth
ESSNet - Embedding-based Scalable Segmentation Network https://github.com/shipra25jain/ESSNet
Code for NeurIPS 2020 article "Contrastive learning of global and local features for medical image segmentation with limited annotations" https://github.com/krishnabits001/domain_specific_cl
PyTorch implementation of Foveation for Segmentation of Ultra-High Resolution Images https://github.com/lxasqjc/Foveation-Segmentation
Learning RGB-D Feature Embeddings for Unseen Object Instance Segmentation https://github.com/NVlabs/UnseenObjectClustering
Code for the paper "Reinforced Active Learning for Image Segmentation" https://github.com/ArantxaCasanova/ralis
Code for our method RePRI for Few-Shot Segmentation. Paper at http://arxiv.org/abs/2012.06166 https://github.com/mboudiaf/RePRI-for-Few-Shot-Segmentation
Semi-supervised Medical Image Segmentation through Dual-task Consistency https://github.com/HiLab-git/DTC
Copy-paste augmentation for segmentation and detection tasks https://github.com/conradry/copy-paste-aug
Hybrid Eloss for object segmentation in PyTorch https://github.com/GewelsJI/Hybrid-Eloss
DeepCrack: A Deep Hierarchical Feature Learning Architecture for Crack Segmentation, Neurocomputing.
https://github.com/yhlleo/DeepCrack
ESANet: Efficient RGB-D Semantic Segmentation for Indoor Scene Analysis https://github.com/TUI-NICR/ESANet
This repository includes the official project of TransUNet, presented in our paper: TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation. https://github.com/Beckschen/TransUNet
Official implementation of "Video Object Segmentation with Adaptive Feature Bank and Uncertain-Region Refinement", https://github.com/xmlyqing00/AFB-URR
https://github.com/saic-vul/ritm_interactive_segmentation
SwiftNet: Real-time Video Object Segmentation https://arxiv.org/abs/2102.04604
Unsupervised Semantic Segmentation by Contrasting Object Mask Proposals https://github.com/wvangansbeke/Unsupervised-Semantic-Segmentation
DoubleU-Net for Semantic Image Segmentation in TensorFlow Keras https://github.com/DebeshJha/2020-CBMS-DoubleU-Net
https://github.com/OFRIN/PuzzleCAM
Pytorch Code for "Medical Transformer: Gated Axial-Attention for Medical Image Segmentation" https://github.com/jeya-maria-jose/Medical-Transformer
[NeurIPS 2020] Disentangling Human Error from the Ground Truth in Segmentation of Medical Images https://github.com/moucheng2017/Learn_Noisy_Labels_Medical_Images
弱监督分割相关文献资源列表 https://github.com/YimingCuiCuiCui/awesome-weakly-supervised-segmentation
ECCV 2020 | OCRNet化解语义分割上下文信息缺失难题 https://weibo.com/ttarticle/p/show?id=2309404540050343067737
Convolution-Free Medical Image Segmentation using Transformers https://arxiv.org/abs/2102.13645
《MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers》(2020) github.com/conradry/max-deeplab
TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation github.com/Beckschen/TransUNet
Medical Transformer: Gated Axial-Attention for Medical Image Segmentation github.com/jeya-maria-jose/Medical-Transformer
Weakly Supervised Instance Segmentation for Videos with Temporal Mask Consistency https://www.arxiv-vanity.com/papers/2103.12886/
github.com/Epiphqny/VisTR
《Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion》(CVPR 2021) github.com/hkchengrex/MiVOS
《Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation》(CVPR 2021) github.com/microsoft/ProDA
《SA-UNet: Spatial Attention U-Net for Retinal Vessel Segmentation》(2020) github.com/clguo/SA-UNet
《Linear Attention Mechanism: An Efficient Attention for Semantic Segmentation》(2020) github.com/lironui/Linear-Attention-Mechanism
https://www.arxiv-vanity.com/papers/2103.14968
CoreML语义分割实例 github.com/tucan9389/SemanticSegmentation-CoreML
图像分割损失函数集 github.com/JunMa11/SegLoss
Hierarchical Pyramid Representations for Semantic Segmentation https://www.arxiv-vanity.com/papers/2104.01792
基于Gluoncv CV toolkit的语义分割推断API github.com/BMW-InnovationLab/BMW-Semantic-Segmentation-Inference-API-GPU-CPU
ZeroCostDL4Mic：用深度学习让显微镜实验大众化(分割、目标检测、去噪、超分辨率和图像到图像变换) https://www.nature.com/articles/s41467-021-22518-0
Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers (CVPR 2021) github.com/lkeab/BCNet
Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers (2020) github.com/920232796/SETR-pytorch
USD-Seg:Learning Universal Shape Dictionary for Realtime Instance Segmentation (2020) github.com/YoruCathy/USDSeg-FCOS
A Comprehensive Analysis of Weakly-Supervised Semantic Segmentation in Different Image Domains github.com/lyndonchan/wsss-analysis
《Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentation》(CVPR 2021) github.com/jbeomlee93/AdvCAM
《Semi-supervised Semantic Segmentation with Directional Context-aware Consistency》(CVPR 2021) github.com/Jia-Research-Lab/Context-Aware-Consistency
《DropLoss for Long-Tail Instance Segmentation》(AAAI 2021) github.com/timy90022/DropLoss
《HyperSeg: Patch-wise Hypernetwork for Real-time Semantic Segmentation》(CVPR 2021) github.com/YuvalNirkin/hyperseg
《MultiResUNet: Rethinking the U-Net architecture for multimodal biomedical image segmentation》(2020) github.com/nibtehaz/MultiResUNet
github.com/AllentDan/SegmentationCpp
RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Features (CVPR 2021) github.com/zhanggang001/RefineMask
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion (CVPR 2021) github.com/hkchengrex/Scribble-to-Mask
Rethinking BiSeNet For Real-time Semantic Segmentation github.com/MichaelFan01/STDC-Seg
Segmenter: Transformer for Semantic Segmentation https://www.arxiv-vanity.com/papers/2105.05633/ github.com/rstrudel/segmenter
Omnimatte: Associating Objects and Their Effects in Video https://www.arxiv-vanity.com/papers/2105.06993
《SNE-RoadSeg: Incorporating Surface Normal Information into Semantic Segmentation for Accurate Freespace Detection》(ECCV 2020) github.com/hlwang1124/SNE-RoadSeg
《ISTR: End-to-End Instance Segmentation via Transformers》(2021) github.com/hujiecpp/ISTR
Regularized Densely-Connected Pyramid Network for Salient Instance Segmentation github.com/yuhuan-wu/RDPNet
Discriminative Region Suppression for Weakly-Supervised Semantic Segmentation (AAAI 2021) github.com/qjadud1994/DRS
《Self-supervised Augmentation Consistency for Adapting Semantic Segmentation》(CVPR 2021) github.com/visinf/da-sac
《Zero-shot Instance Segmentation》(CVPR 2021) github.com/zhengye1995/Zero-shot-Instance-Segmentation
《Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion》(CVPR 2021) github.com/hkchengrex/Mask-Propagation
《Segmenter: Transformer for Semantic Segmentation》(2021) github.com/rstrudel/segmenter
《A Large-Scale Benchmark for Food Image Segmentation》(2021) github.com/XiongweiWu/FoodSeg-Benchmark
《DCT-Mask: Discrete Cosine Transform Mask Representation for Instance Segmentation》(CVPR 2021) github.com/aliyun/DCT-Mask
《A Closer Look at Self-training for Zero-Label Semantic Segmentation》(2021) github.com/giuseppepastore10/STRICT
《Finding an Unsupervised Image Segmenter in each of your Deep Generative Models》(2021) github.com/lukemelas/pytorch-pretrained-gans
《PPR10K: A Large-Scale Portrait Photo Retouching Dataset with Human-Region Mask and Group-Level Consistency》(CVPR 2021) github.com/csjliang/PPR10K
github.com/tinyalpha/BPR
《SOLQ: Segmenting Objects by Learning Queries》(2021) github.com/megvii-research/SOLQ
Medical Image Segmentation using Squeeze-and-Expansion Transformers github.com/askerlee/segtran
《Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision》(CVPR 2021) github.com/charlesCXK/TorchSemiSeg
《SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers》 github.com/NVlabs/SegFormer
《Adaptive Prototype Learning and Allocation for Few-Shot Segmentation》(CVPR 2021) github.com/Reagan1311/ASGNet
《Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation》(2021) github.com/hkchengrex/STCN
《Regularized Loss for Weakly Supervised Single Class Semantic Segmentation》(ECCV 2020) github.com/morduspordus/SingleClassRL
《Real-time Semantic Segmentation with Fast Attention》 github.com/feinanshan/FANet
《Channel-wise Distillation for Semantic Segmentation》(2020) github.com/irfanICMLL/CWD
New, improved Detectron2 Mask R-CNN baselines https://ai.facebook.com/blog/advancing-computer-vision-research-with-new-detectron2-mask-r-cnn-baselines/
Foreground-Aware Stylization and Consensus Pseudo-Labeling for Domain Adaptation of First-Person Hand Segmentation #手语 github.com/ut-vision/FgSty-CPL
A topological solution to object segmentation and tracking https://www.arxiv-vanity.com/papers/2107.02036
《Robust Instance Segmentation through Reasoning about Multi-Object Occlusion》(CVPR 2021) github.com/XD7479/Multi-Object-Occlusion
github.com/warmspringwinds/segmentation_in_style
Open-World Entity Segmentation github.com/dvlab-research/Entity
UVO：未识别视频目标、开放世界目标分割新基准 sites.google.com/view/unidentified-video-object/home
github.com/easton-cau/SOTR
Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentation
https://arxiv.org/abs/2108.11249
ISNet: Integrate Image-Level and Semantic-Level Context for Semantic Segmentation github.com/SegmentationBLWX/sssegmentation
Lightning Kitti：用Pytorch-Lightning实现的语义分割 github.com/borisdayma/lightning-kitti
Keras实例：DeepLabV3+多类语义分割 https://keras.io/examples/vision/deeplabv3_plus/
RobustVideoMatting技术引入了一种强大、实时、高分辨率的人物视频抠图方法，使用循环神经网络，在处理视频流时有时间记忆，可在任意视频上做实时高清抠像。在 Nvidia GTX 1080Ti 上实现 4K 76FPS 和 HD 104FPS。 github.com/PeterL1n/RobustVideoMatting/
Hierarchical Memory Matching Network for Video Object Segmentation github.com/Hongje/HMMN
《Mask-aware IoU for Anchor Assignment in Real-time Instance Segmentation》 github.com/kemaloksuz/Mask-aware-IoU
Dense Unsupervised Learning for Video Segmentation github.com/visinf/dense-ulearn-vos
Awesome Image Matting：深度学习抠图文献代码资源列表 github.com/wchstrife/Awesome-Image-Matting
End-to-End Referring Video Object Segmentation with Multimodal Transformers github.com/mttr2021/MTTR
PP-HumanSeg: Connectivity-Aware Portrait Segmentation with a Large-Scale Teleconferencing Video Dataset https://arxiv.org/abs/2112.07146 https://github.com/PaddlePaddle/PaddleSeg
深度学习视频分割相关资源集 github.com/tfzhou/VS-Survey
Pixel 6手机上人像模式自拍的精确Alpha抠图 https://ai.googleblog.com/2022/01/accurate-alpha-matting-for-portrait.html
Semantic Segmentation：PyTorch实现的SOTA语义分割模型集 github.com/sithu31296/semantic-segmentation
3D-Point-Clouds - 3D点云目标检测&语义分割-SOTA方法,代码,论文,数据集等 github.com/HuangCongQing/3D-Point-Clouds
视频目标分割(VOS)文献大列表 github.com/suhwan-cho/awesome-video-object-segmentation
GroupViT: Semantic Segmentation Emerges from Text Supervision https://arxiv.org/abs/2202.11094
Efficient Video Instance Segmentation via Tracklet Query and Proposal https://arxiv.org/abs/2203.01853
Transformer检测与分割文献列表 github.com/IDEACVR/awesome-detection-transformer
HybridNets: End-to-End Perception Network https://arxiv.org/abs/2203.09035
Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinity https://arxiv.org/abs/2204.06107
Temporally Efficient Vision Transformer for Video Instance Segmentation https://arxiv.org/abs/2204.08412
PP-Matting: High-Accuracy Natural Image Matting https://arxiv.org/abs/2204.09433
语义分割实战教程 Semantic segmentation - In this tutorial, you will perform inference across 10 well-known pre-trained semantic segmentors and fine-tune on a custom dataset. Design and train your own segmentor. github.com/IbrahimSobh/Segmentation
Guess What Moves: Unsupervised Video and Image Segmentation by Anticipating Motion https://arxiv.org/abs/2205.07844
Decoder Denoising Pretraining for Semantic Segmentation https://arxiv.org/abs/2205.11423
https://arxiv.org/abs/2205.14929
[CV]《Improving Semantic Segmentation in Transformers using Hierarchical Inter-Level Attention》G Leung, J Gao, X Zeng, S Fidler [University of Toronto] (2022) https://arxiv.org/abs/2207.02126
[CV]《XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model》H K Cheng, A G. Schwing [University of Illinois Urbana-Champaign] (2022) https://arxiv.org/abs/2207.07115
[CV]《Highly Accurate Dichotomous Image Segmentation》X Qin, H Dai, X Hu, D Fan, L Shao, a L V Gool [MBZUAI & TUM & ETH Zurich & Terminus Group] (2022) https://arxiv.org/abs/2203.03041
【视频目标分割参考项目列表】’Awesome-Referring-Video-Object-Segmentation - Referring Video Object Segmentation Repos' by JerryX1110 GitHub: github.com/JerryX1110/awesome-rvos
【CBIM-Medical-Image-Segmentation：PyTorch医学图像分割框架】’CBIM-Medical-Image-Segmentation' by yhygao GitHub: github.com/yhygao/CBIM-Medical-Image-Segmentation
[CV]《MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Training》D Huang, Z Yu, A Anandkumar [NVIDIA] (2022) https://arxiv.org/abs/2208.02245
[CV]《Per-Clip Video Object Segmentation》K Park, S Woo, S W Oh, I S Kweon, J Lee [KAIST & Adobe Research] (2022) https://arxiv.org/abs/2208.01924
【TotalSegmentator：对CT图像中104种重要解剖结构进行可靠分割的工具】’TotalSegmentator - Tool for robust segmentation of 104 important anatomical structures in CT images' by Jakob Wasserthal GitHub: github.com/wasserth/TotalSegmentator
[CV]《Efficient Heterogeneous Video Segmentation at the Edge》J M Lin, S Pisarchyk, J Lee, D Tian, T Hou, K Raveendran, R Sarokin, G Sung, T Tolley, M Grundmann [Google] (2022) https://arxiv.org/abs/2208.11666
[CV]《VMFormer: End-to-End Video Matting with Transformer》J Li, V Goel, M Ohanyan, S Navasardyan, Y Wei, H Shi [University of Oregon & BJTU & Picsart AI Research (PAIR)] (2022) https://arxiv.org/abs/2208.12801
【视频实例分割相关文献资源列表】’Awesome-Video-Instance-Segmentation-Papers' by Qing Zhong GitHub: github.com/QingZhong1996/Awesome-Video-Instance-Segmentation-Papers
[CV]《TokenCut: Segmenting Objects in Images and Videos with Self-supervised Transformer and Normalized Cut》Y Wang, X Shen, Y Yuan... [CNRS & Tencent AI Lab & MIT CSAIL & ...] (2022) https://arxiv.org/abs/2209.00383
【Robust Video Matting (RVM)：强大稳定的视频抠图】’Robust Video Matting (RVM) - Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!' by Peter Lin GitHub: github.com/PeterL1n/RobustVideoMatting
[CV]《SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation》M Guo, C Lu, Q Hou, Z Liu, M Cheng, S Hu [Tsinghua University & Nankai University & Fitten Tech] (2022) https://arxiv.org/abs/2209.08575
【DetHub：开源目标检测/实例分割实验中心】'DetHub - open source object detection / instance segmentation experiments hub’ by takuoko GitHub: github.com/okotaku/dethub
[CV]《NamedMask: Distilling Segmenters from Complementary Foundation Models》G Shin, W Xie, S Albanie [University of Oxford & University of Cambridge] (2022) https://arxiv.org/abs/2209.11228
【GeoSeg：基于PyTorch、pytorch lightning和timm的开源语义分割工具箱，主要致力于开发用于遥感图像分割的高级视觉Transformer】'GeoSeg - an open-source semantic segmentation toolbox based on PyTorch, pytorch lightning and timm, which mainly focuses on developing advanced Vision Transformers for remote sensing image segmentation' by Libo Wang GitHub: github.com/WangLibo1995/GeoSeg
'Awesome Box-supervised Instance Segmentation. - Awesome box-supervised instance segmentation papers.' by sunshine.lwt GitHub: github.com/LiWentomng/Box-supervised-instance-segmentation
【BoxInstSeg：旨在提供最先进的框监督实例分割算法的工具包】’BoxInstSeg - A toolbox for box-supervised instance segmentation.' by sunshine.lwt GitHub: github.com/LiWentomng/BoxInstSeg
【Anime Segmentation：动漫人物分割】’Anime Segmentation - high-accuracy segmentation for anime character' by SkyTNT GitHub: github.com/SkyTNT/anime-segmentation
[CV]《Peekaboo: Text to Image Diffusion Models are Zero-Shot Segmentors》R Burgert, K Ranasinghe, X Li, M S. Ryoo [Stony Brook University] (2022) https://arxiv.org/abs/2211.13224
【CLIPSeg零样本图像分割】《Zero-shot image segmentation with CLIPSeg》 https://huggingface.co/blog/clipseg-zero-shot
[CV]《TarViS: A Unified Approach for Target-based Video Segmentation》A Athar, A Hermans, J Luiten, D Ramanan, B Leibe [RWTH Aachen University & CMU] (2023) https://arxiv.org/abs/2301.02657
'Semantic Sementation model within ML pipeline' by Chansung Park GitHub: github.com/deep-diver/semantic-segmentation-ml-pipeline
[CV]《Box2Mask: Box-supervised Instance Segmentation via Level-set Evolution》W Li, W Liu, J Zhu, M Cui, R Yu, X Hua, L Zhang [Zhejiang University & Alibaba Group & The Hong Kong Polytechnic University] (2022) https://arxiv.org/abs/2212.01579
[CV]《Deep Learning for Human Parsing: A Survey》X Zhang, X Zhu, M Tang, Z Lei [Chinese Academy of Sciences] (2023) https://arxiv.org/abs/2301.12416
[CV]《Contour-based Interactive Segmentation》D Galeev, P Popenova, A Vorontsova, A Konushin [Samsung AI Center] (2023)
https://arxiv.org/abs/2302.06353
【半监督语义分割相关文献资源列表】’Awesome-Semi-Supervised-Semantic-Segmentation - A summary of recent semi-supervised semantic segmentation methods' BB CHAN GitHub: github.com/BBBBchan/Awesome-Semi-Supervised-Semantic-Segmentation
[CV]《Open-world Instance Segmentation: Top-down Learning with Bottom-up Supervision》T Kalluri, W Wang, H Wang, M Chandraker, L Torresani, D Tran [Meta AI & UC San Diego] (2023) 提出一种新的开放世界实例分割方法，结合自下而上和自上而下的学习，实现了对最先进方法的显著改进。 https://arxiv.org/abs/2303.05503
Grounded-Segment-Anything 上次推荐的Meta的Segment Anything 微博正文 我把它比喻成AI抠图还是太狭隘了，其实它最强大的还是物体识别，以前在识别物体是都是针对特定物体的识别，而现在Segment Anything的能力是任意物体的识别，不必事先针对某个特定物体的训练 这带来很多可能，比如说可以应用在自动驾驶帮助识别路面物体，可以在军事上用来标注卫星拍出来的各种目标。 现在已经有国内的开发者把Segment Anything（从图片识别分离对象）和BLIP（一个图片生成文字模型）、Stable Diffusion（AI画图工具）集成在一起，将图片的“分割”、“检测”和“生成”三种能力组合在一起，产生很多新的有价值的应用场景，比如：
- 替换图片中的物体生成新的图片
- 对图片中的物体生成标签 作者博文：最强Zero-Shot视觉应用：Grounding DINO + Segment Anything + Stable Diffusion 项目地址： 🔗 github.com/IDEA-Research/Grounded-Segment-Anything
【Magic Copy：一个 Chrome 扩展程序，利用 Meta 的 "Segment Anything"，从图像中提取前景目标并将其复制到剪贴板】'Magic Copy -一个 Chrome 扩展程序，使用 Meta 的 "Segment Anything" 模型，从图像中提取前景对象并将其复制到剪贴板。.' Kevin Wang GitHub: github.com/kevmo314/magic-copy
【SegDrawer：基于Segment Anything Model (SAM)的简单图片分割静态页面前端】’SegDrawer - Simple static web-based mask drawer, supporting semantic drawing with Segment Anything Model (SAM).' Harry GitHub: github.com/lujiazho/SegDrawer
【Prompt-Segment-Anything：基于Segment Anything的零样本实例分割】’Prompt-Segment-Anything - This is an implementation of zero-shot instance segmentation using Segment Anything.' Rockey GitHub: github.com/RockeyCoss/Prompt-Segment-Anything
'Awesome-Anything - AI methods for Anything: AnyObject, AnyGeneration, AnyModel, AnyTask' Gongfan Fang GitHub: github.com/VainF/Awesome-Anything
【Segment Anything EO tools：基于 Meta AI Segment Anything 的地球观测工具】'Segment Anything EO tools - Earth observation tools for Meta AI Segment Anything' Aliaksandr Hancharenka GitHub: github.com/aliaksandr960/segment-anything-eo
【Segment Anything Model (SAM) 相关扩展/项目/应用大列表】’Awesome-segment-anything-extensions - Segment-anything related awesome extensions/projects/repos.' Xiaohao XU GitHub: github.com/JerryX1110/awesome-segment-anything-extensions
’Grounded-Segment-Anything - Marrying Grounding DINO with Segment Anything & Stable Diffusion & BLIP & Whisper' IDEA-Research GitHub: github.com/IDEA-Research/Grounded-Segment-Anything
lama-cleaner
Lama Cleaner： 一个由SOTA AI模型驱动的免费开源图像清理工具 这个工具可以本地运行，帮助你擦除图片中你不想要的内容，移除背景、面部修复等工作 前段时间刚好用过，有gpu版本和cpu版本的，处理速度比较依赖设备，cpu大概十几秒完成一次拔除，rtx3070 2-3s左右完成一次擦除，效果都挺好。本地部署略微麻烦一点，同款替代的在线产品有magic eraser和remove bg，免费免登录的的，效果也很好。 🔗 github.com/Sanster/lama-cleaner
【Zero-shot panoptic segmentation using SAM：Segment Anything (SAM) + Grounded DINO 零样本目标分割】’Zero-shot panoptic segmentation using SAM - Combining Segment Anything (SAM) with Grounded DINO for zero-shot object detection and CLIPSeg for zero-shot segmentation' Segments.ai GitHub: github.com/segments-ai/panoptic-segment-anything
【Segment Anything相关资源大列表】’Awesome Segment Anything - Tracking and collecting papers/projects/others related to Segment Anything.' Dylan GitHub: github.com/Hedlen/awesome-segment-anything
【Anything-3D：Segment Anything + 3D】’Anything-3D - Segment-Anything + 3D. Let's lift the anything to 3D.' Anything-of-Anything GitHub: github.com/Anything-of-anything/Anything-3D
【napari-segment-anything：SAM的本地Qt UI界面】’napari-segment-anything - Segment Anything Model (SAM) native Qt UI' Jordão Bragantini GitHub: github.com/JoOkuma/napari-segment-anything
【Transformer 视觉分割相关资源列表】’Transformer-Based Visual Segmentation: A Survey' by Xiangtai Li GitHub: github.com/lxtGH/Awesome-Segmenation-With-Transformer
【SAM及相关研究的论文、源代码和工具列表】’Awesome-Segment-Anything - A collection of project, papers, and source code for Meta AI's Segment Anything Model (SAM) and related studies.' GitHub: github.com/Vision-Intelligence-and-Robots-Group/Awesome-Segment-Anything
提出一种基于单张图像的无需训练的方法，名为PerSAM，用于将Segment Anything Model(SAM)个性化，从而能针对特定的视觉概念进行图像分割，且能够在10秒内进行优化，可在个性化场景中有效自适应SAM。 https://arxiv.org/abs/2305.03048 [CV]《Personalize Segment Anything Model with One Shot》R Zhang, Z Jiang, Z Guo, S Yan, J Pan, H Dong, P Gao, H Li [Shanghai Artificial Intelligence Laboratory & Tencent Youtu Lab] (2023)
【Segment Anything(SAM)相关工作列表】’Awesome Segment Anything' by Li Liu GitHub: github.com/liliu-avril/Awesome-Segment-Anything
【SegmentAnything for Microscopy：基于SAM的显微镜分割和跟踪工具】'SegmentAnything for Microscopy - Segment Anything for Microscopy' computational-cell-analytics GitHub: github.com/computational-cell-analytics/micro-sam
【Segment Every Grain：基于 SAM 的谷物(或类似谷物的目标)图像实例分割模型】'Segment Every Grain - A SAM-based model for instance segmentation of images of grains' Zoltán Sylvester Sylvester GitHub: github.com/zsylvester/segmenteverygrain
【SAMIST：使用SAM进行图像分割的Python GUI工具。使用SAMIST，可以选择模型类型、加载图像进行分割，并导出生成的蒙版】’SAMIST - Segment Anything Model (SAM) Image Segmentation Tool - SAMIST. Python GUI for image segmentation using SAM by Meta AI.' Alexander Dibrov GitHub: github.com/dibrale/samist
Matting Anything Model(MAM)是一个能处理各种类型图像抠图任务的模型，利用了Segment Anything Model(SAM)的特征图，并采用一个轻量的Mask-to-Matte(M2M)模块来预测alpha matte，实验结果表明，MAM在各种图像抠图基准测试中都达到了与专门抠图模型相当的性能。
https://arxiv.org/abs/2306.05399 [CV]《Matting Anything》J Li, J Jain, H Shi [UIUC & Oregon] (2023) https://github.com/SHI-Labs/Matting-Anything
提出一种加速的替代方法，通过将任务重新构造为风格生成和提示，并直接使用SAM作者发布的SA-1B数据集的1/50来训练现有的实例分割方法，实现了与SAM方法相当的性能，但运行速度快50倍。 https://arxiv.org/abs/2306.12156 [CV]《Fast Segment Anything》X Zhao, W Ding, Y An, Y Du, T Yu, M Li, M Tang, J Wang [Chinese Academy of Sciences] (2023)
【SAM Exporter：快速导出Segment Anything模型至不同格式，方便使用，可用于快速推理】'SAM Exporter - Export Segment Anything Models to ONNX' Viet-Anh, Nguyen GitHub: github.com/vietanhdev/samexporter
FastSAM，快速分割一切 地址：github.com/CASIA-IVA-Lab/FastSAM 这个项目基于CNN，其性能与 之前Facebook提出的 SAM （分割一切）类似，但运行速度提高了 50 倍。
【用Tensorrt加速SAM模型推理】’Segment anything tensorrt - Accelerate segment anything model inference using Tensorrt 8.6.1.6' BooHwang GitHub: github.com/BooHwang/segment_anything_tensorrt
【SAM.cpp：使用纯C/C++实现的Meta’s Segment Anything(SAM)分割模型推理】'SAM.cpp' by Yavor Ivanov GitHub: github.com/YavorGIvanov/sam.cpp
[CV]《High-Quality Entity Segmentation》L Qi, J Kuen, W Guo, T Shen, J Gu, J Jia, Z Lin, M Yang [The University of California, Merced & Adobe Research & QQ Brower Lab] (2022) https://arxiv.org/abs/2211.05776 提出一种新的高质量实体分割数据集和CropFormer模型，通过融合高分辨率图像裁剪和完整图像来改进分割结果，并取得了显著的性能提升。
【SAM批量离线推断版】’Segment anything ... Fast - A batched offline inference oriented version of segment-anything' PyTorch Labs GitHub: github.com/pytorch-labs/segment-anything-fast
通过自蒸馏的方式改进了图像特征学习，提出SILC模型，在多个计算机视觉任务上取得了显著的性能提升，特别是在零样本和开放词表分割任务上。 https://arxiv.org/abs/2310.13355 [CV]《SILC: Improving Vision Language Pretraining with Self-Distillation》M F Naeem, Y Xian, X Zhai, L Hoyer, L V Gool, F Tombari [ETH Zurich & Google & Google Deepmind] (2023)
【用PyTorch将Segment Anything加速8倍】
- PyTorch团队使用纯PyTorch优化实现了Meta的Segment Anything(SAM)模型，比原实现快8倍，同时保持了准确性。
- 实现中使用了多项新的PyTorch特性：Torch.compile、GPU量化、缩放点积注意力、半结构化稀疏、嵌套张量和Triton定制算子。
- Torch.compile通过融合操作加速；GPU量化通过降低精度加速；缩放点积注意力实现内存高效的注意力机制。
- 半结构化稀疏可在保持密集输出的同时节省50%内存；嵌套张量可高效处理不同大小的批次；Triton可自定义GPU算子。
- 通过这些技术的组合，实现了SAM模型在纯PyTorch下的性能提升，包括吞吐量提高和内存开销降低。
- 证明了PyTorch原生的各项新特性能有效地加速生成式AI模型，未来将继续分享这方面的经验。 《Accelerating Generative AI with PyTorch: Segment Anything, Fast | PyTorch》 https://pytorch.org/blog/accelerating-generative-ai/
【视频目标分割相关论文资源列表】’Awesome Video Object Segmentation - A curated list of video object segmentation (vos) papers, datasets, and projects.' Mingqi Gao GitHub: github.com/gaomingqi/Awesome-Video-Object-Segmentation