语义分割 - Semantic Segmentation Papers

1. Semantic Segmentation

  1. Gated-SCNN: Gated Shape CNNs for Semantic Segmentation - 2019 - NVIDIA <Paper> <Project>
  2. FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation - 2019 <Paper> <Project> <Code-PyTorch>
  3. Structured Knowledge Distillation for Semantic Segmentation - CVPR2019 <Paper>
  4. Co-Occurrent Features in Semantic Segmentation - CVPR2019 <Paper>
  5. Semantic Projection Network for Zero- and Few-Label Semantic Segmentation - CVPR2019 <Paper>
  6. Context-Reinforced Semantic Segmentation - CVPR2019 <Paper>
  7. SwiftNet - In Defense of Pre-trained ImageNet Architectures for Real-time Semantic Segmentation of Road-driving Images - CVPR2019 <Paper> <Code-PyTorch>
  8. All About Structure: Adapting Structural Information Across Domains for Boosting Semantic Segmentation - CVPR2019 <Paper>
  9. Not All Areas Are Equal: Transfer Learning for Semantic Segmentation via Hierarchical Region Selection - CVPR2019 <Paper>
  10. Learning Semantic Segmentation From Synthetic Data: A Geometrically Guided Input-Output Adaptation Approach - CVPR2019 <Paper>
  11. Box-Driven Class-Wise Region Masking and Filling Rate Guided Loss for Weakly Supervised Semantic Segmentation - CVPR2019 <Paper>
  12. Cyclic Guidance for Weakly Supervised Joint Detection and Segmentation - CVPR2019 <Paper>
  13. Geometry-Aware Distillation for Indoor Semantic Segmentation - CVPR2019 <Paper>
  14. Seamless Scene Segmentation - CVPR2019 <Paper>
  15. ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation - CVPR2019 <Paper> <Code-Github>
  16. Taking a Closer Look at Domain Shift: Category-Level Adversaries for Semantics Consistent Domain Adaptation - CVPR2019 <Paper>
  17. PartNet: A Large-Scale Benchmark for Fine-Grained and Hierarchical Part-Level 3D Object Understanding - CVPR2019 <Paper> <Homepage>
  18. A Cross-Season Correspondence Dataset for Robust Semantic Segmentation - CVPR2019 <Paper>
  19. DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation-Megvii-2019 <Paper>
  20. DADA: Depth-aware Domain Adaptation in Semantic Segmentation - 2019 <Paper>
  21. GFF: Gated Fully Fusion for Semantic Segmentation - 2019 <Paper>
  22. DSNet: An Efficient CNN for Road Scene Segmentation - 2019 <Paper>
  23. FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inference - CVPR2019 <Paper>
  24. An efficient solution for semantic segmentation: ShuffleNet V2 with atrous separable convolutions - 2019 <Paper>
  25. Fast-SCNN: Fast Semantic Segmentation Network - 2019 <Paper>
  26. Data augmentation using learned transforms for one-shot medical image segmentation - CVPR2019 <Paper>
  27. MultiResUNet : Rethinking the U-Net Architecture for Multimodal Biomedical Image Segmentation - 2019 <Paper>
  28. CCNet: Criss-Cross Attention for Semantic Segmentation - 2018 <Paper> <Code-PyTorch>
  29. A PyTorch Semantic Segmentation Toolbox - 2018 <Paper> <Code-PyTorch>
  30. ShelfNet for Real-time Semantic Segmentation - 2018 <Paper> <Code-PyTorch>
  31. Unsupervised Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training - ECCV2018 <Paper> <Project> <Code-MXNet>
  32. Searching for Efficient Multi-Scale Architectures for Dense Image Prediction - 2018 - Deeplab <Paper> <Code-Deeplab-Tensorflow>
  33. Light-Weight RefineNet for Real-Time Semantic Segmentation - bmvc2018 <Paper> <Code-Torch>
  34. Dual Attention Network for Scene Segmentation - 2018 <Paper>
  35. BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation - ECCV 2018 - Face++ <Paper> <Code-PyTorch>
  36. Adaptive Affinity Field for Semantic Segmentation - ECCV2018 <Paper> <HomePage>
  37. Recurrent Iterative Gating Networks for Semantic Segmentation - WACV2019 <Paper>
  38. Dense Decoder Shortcut Connections for Single-Pass Semantic Segmentation - CVPR2018 <Paper>
  39. DenseASPP for Semantic Segmentation in Street Scenes - CVPR2018 <Paper> <Code-PyTorch>
  40. Pyramid Attention Network for Semantic Segmentation - 2018 - Face++ <Paper>
  41. Autofocus Layer for Semantic Segmentation - 2018 <Paper <Code-PyTorch>
  42. ExFuse: Enhancing Feature Fusion for Semantic Segmentation - ECCV2018 - Face++ <Paper>
  43. DifNet: Semantic Segmentation by Diffusion Networks - 2018 <Paper>
  44. Convolutional CRFs for Semantic Segmentation - 2018 <Paper><Code-PyTorch>
  45. ContextNet: Exploring Context and Detail for Semantic Segmentation in Real-time - 2018 <Paper>
  46. Learning a Discriminative Feature Network for Semantic Segmentation - CVPR2018 - Face++ <Paper>
  47. Vortex Pooling: Improving Context Representation in Semantic Segmentation - 2018 <Paper>
  48. Fully Convolutional Adaptation Networks for Semantic Segmentation - CVPR2018 <Paper>
  49. A Multi-Layer Approach to Superpixel-based Higher-order Conditional Random Field for Semantic Image Segmentation - 2018 <Paper>
  50. Context Encoding for Semantic Segmentation - 2018 <Paper> <Code-PyTorch> <Code-PyTorch2> <Slides>
  51. ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation - ECCV2018 <Paper> <Code-Pytorch>
  52. Dynamic-structured Semantic Propagation Network - 2018 - CMU <Paper>
  53. ShuffleSeg: Real-time Semantic Segmentation Network-2018 <Paper> <Code-TensorFlow>
  54. RTSeg: Real-time Semantic Segmentation Comparative Study - 2018 <Paper> <Code-TensorFlow>
  55. Decoupled Spatial Neural Attention for Weakly Supervised Semantic Segmentation - 2018 <Paper>
  56. DeepLabV3+:Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation - 2018 - Google <Paper> <Code-Tensorflow> <Code-Karas>
  57. Adversarial Learning for Semi-Supervised Semantic Segmentation - 2018 <Paper> <Code-PyTorch>
  58. Locally Adaptive Learning Loss for Semantic Image Segmentation - 2018 <Paper>
  59. Learning to Adapt Structured Output Space for Semantic Segmentation - 2018 <Paper>
  60. Improved Image Segmentation via Cost Minimization of Multiple Hypotheses - 2018 <Paper> <Code-Matlab>
  61. TernausNet: U-Net with VGG11 Encoder Pre-Trained on ImageNet for Image Segmentation - 2018 - Kaggle <Paper> <Code-PyTorch> <Kaggle-Carvana Image Masking Challenge>
  62. Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation - 2018 - Google <Paper>
  63. End-to-end Detection-Segmentation Network With ROI Convolution - 2018 <Paper>
  64. Mix-and-Match Tuning for Self-Supervised Semantic Segmentation - AAAI2018 <Project> <Paper> <Code-Caffe>
  65. Learning to Segment Every Thing-2017 <Paper> <Code-Caffe2> <Code-PyTorch>
  66. Deep Dual Learning for Semantic Image Segmentation-2017 <Paper>
  67. Scene Parsing with Global Context Embedding - ICCV2017 <Paper>
  68. FoveaNet: Perspective-aware Urban Scene Parsing - ICCV2017 <Paper>
  69. Segmentation-Aware Convolutional Networks Using Local Attention Masks - 2017 <Paper> <Code-Caffe> <Project>
  70. Stacked Deconvolutional Network for Semantic Segmentation-2017 <Paper>
  71. Semantic Segmentation via Structured Patch Prediction, Context CRF and Guidance CRF - CVPR2017 <Paper> <Caffe-Code>
  72. BlitzNet: A Real-Time Deep Network for Scene Understanding-2017 <Project> <Code-Tensorflow> <Paper>
  73. Efficient Yet Deep Convolutional Neural Networks for Semantic Segmentation -2017 <Paper> <Code-Caffe>
  74. LinkNet: Exploiting Encoder Representations for Efficient Semantic Segmentation - 2017 <Paper> <Code-Torch>
  75. Rethinking Atrous Convolution for Semantic Image Segmentation-2017(DeeplabV3) <Paper>
  76. Learning Object Interactions and Descriptions for Semantic Image Segmentation-2017 <Paper>
  77. Pixel Deconvolutional Networks-2017 <Code-Tensorflow> <Paper>
  78. Dilated Residual Networks-2017 <Paper> <Code-PyTorch>
  79. Recurrent Scene Parsing with Perspective Understanding in the Loop - 2017 <Project> <Paper> <Code-MatConvNet>
  80. A Review on Deep Learning Techniques Applied to Semantic Segmentation-2017 <Paper>
  81. BiSeg: Simultaneous Instance Segmentation and Semantic Segmentation with Fully Convolutional Networks <Paper>
  82. Efficient ConvNet for Real-time Semantic Segmentation - 2017 <Paper>
  83. ICNet for Real-Time Semantic Segmentation on High-Resolution Images-2017 <Project> <Code-Caffe> <Paper> <Video>
  84. Not All Pixels Are Equal: Difficulty-Aware Semantic Segmentation via Deep Layer Cascade-2017 <Paper> <Poster> <Project> <Code-Caffe> <Slides>
  85. Loss Max-Pooling for Semantic Image Segmentation-2017 <Paper>
  86. Annotating Object Instances with a Polygon-RNN-2017 <Project> <Paper>
  87. Feature Forwarding: Exploiting Encoder Representations for Efficient Semantic Segmentation-2017 <Project> <Code-Torch7>
  88. Reformulating Level Sets as Deep Recurrent Neural Network Approach to Semantic Segmentation-2017 <Paper>
  89. Adversarial Examples for Semantic Image Segmentation-2017 <Paper>
  90. Large Kernel Matters - Improve Semantic Segmentation by Global Convolutional Network-2017 <Paper>
  91. Label Refinement Network for Coarse-to-Fine Semantic Segmentation-2017 <Paper>
  92. PixelNet: Representation of the pixels, by the pixels, and for the pixels-2017 <Project> <Code-Caffe> <Paper>
  93. LabelBank: Revisiting Global Perspectives for Semantic Segmentation-2017 <Paper>
  94. Progressively Diffused Networks for Semantic Image Segmentation-2017 <Paper>
  95. Understanding Convolution for Semantic Segmentation-2017 <Model-Mxnet> <Mxnet-Code> <Paper>
  96. Predicting Deeper into the Future of Semantic Segmentation-2017 <Paper>
  97. Pyramid Scene Parsing Network-2017 <Project> <Code-Caffe> <Paper> <Slides>
  98. FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation-2016 <Paper>
  99. FusionNet: A deep fully residual convolutional neural network for image segmentation in connectomics-2016 <Code-PyTorch> <Paper>
  100. RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation-2016 <Code-MatConvNet> <Paper> <Code-Pytorch>
  101. Learning from Weak and Noisy Labels for Semantic Segmentation - 2017 <Paper>
  102. The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation <Code-Theano> <Code-Keras1> <Code-Keras2> <Paper>
  103. Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes <Code-Theano> <Paper>
  104. PixelNet: Towards a General Pixel-level Architecture-2016 <Paper>
  105. Recalling Holistic Information for Semantic Segmentation-2016 <Paper>
  106. Semantic Segmentation using Adversarial Networks-2016 <Paper> <Code-Chainer>
  107. Region-based semantic segmentation with end-to-end training-2016 <Paper>
  108. Exploring Context with Deep Structured models for Semantic Segmentation-2016 <Paper>
  109. Better Image Segmentation by Exploiting Dense Semantic Predictions-2016 <Paper>
  110. Boundary-aware Instance Segmentation-2016 <Paper>
  111. Improving Fully Convolution Network for Semantic Segmentation-2016 <Paper>
  112. Deep Structured Features for Semantic Segmentation-2016 <Paper>
  113. DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs-2016 <Project> <Code-Caffe> <Code-Tensorflow> <Code-PyTorch> <Paper>
  114. DeepLab: Semantic Image Segmentation With Deep Convolutional Nets and Fully Connected CRFs-2014 <Code-Caffe1> <Code-Caffe2> <Paper>
  115. Deep Learning Markov Random Field for Semantic Segmentation-2016 <Project> <Paper>
  116. Convolutional Random Walk Networks for Semantic Image Segmentation-2016 <Paper>
  117. ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation-2016 <Code-Caffe1> <Code-Caffe2> <Paper> <Blog>
  118. High-performance Semantic Segmentation Using Very Deep Fully Convolutional Networks-2016 <Paper>
  119. ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation-2016 <Paper>
  120. Object Boundary Guided Semantic Segmentation-2016 <Code-Caffe> <Paper>
  121. Segmentation from Natural Language Expressions-2016 <Project> <Code-Tensorflow> <Code-Caffe> <Paper>
  122. Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation-2016 <Code-Caffe> <Paper>
  123. Global Deconvolutional Networks for Semantic Segmentation-2016 <Paper> <Code-Caffe>
  124. Learning Transferrable Knowledge for Semantic Segmentation with Deep Convolutional Neural Network-2015 <Project> <Code-Caffe> <Paper>
  125. Learning Dense Convolutional Embeddings for Semantic Segmentation-2015 <Paper>
  126. ParseNet: Looking Wider to See Better-2015 <Code-Caffe> <Model-Caffe> <Paper>
  127. Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation-2015 <Project> <Code-Caffe> <Paper>
  128. SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation-2015 <Project> <Code-Caffe> <Paper> <Tutorial1> <Tutorial2>
  129. SegNet: A Deep Convolutional Encoder-Decoder Architecture for Robust Semantic Pixel-Wise Labelling-2015 <Code-Caffe> <Code-Chainer> <Paper>
  130. Semantic Image Segmentation with Task-Specific Edge Detection Using CNNs and a Discriminatively Trained Domain Transform-2015 <Paper>
  131. Semantic Segmentation with Boundary Neural Fields-2015 <Code-Matlab> <Paper>
  132. Semantic Image Segmentation via Deep Parsing Network-2015 <Project> <Paper1> <Paper2> <Slides>
  133. What’s the Point: Semantic Segmentation with Point Supervision-2015 <Project> <Code-Caffe> <Model-Caffe> <Paper>
  134. U-Net: Convolutional Networks for Biomedical Image Segmentation-2015 <Project> <Code+Data> <Code-Keras> <Code-Tensorflow> <Paper> <Notes>
  135. Learning Deconvolution Network for Semantic Segmentation(DeconvNet)-2015 <Project> <Code-Caffe> <Paper> <Slides>
  136. Multi-scale Context Aggregation by Dilated Convolutions-2015 <Project> <Code-Caffe> <Code-Keras> <Paper> <Notes>
  137. ReSeg: A Recurrent Neural Network-based Model for Semantic Segmentation-2015 <Code-Theano> <Paper>
  138. BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation-2015 <Paper>
  139. Feedforward semantic segmentation with zoom-out features-2015 <Code-Torch> <Paper> <Video>
  140. Conditional Random Fields as Recurrent Neural Networks-2015 <Project> <Code-Caffe1> <Code-Caffe2> <Demo> <Paper1> <Paper2>
  141. Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation-2015 <Paper>
  142. Fully Convolutional Networks for Semantic Segmentation-2015 <Code-Caffe> <Model-Caffe> <Code-Tensorflow1> <Code-Tensorflow2> <Code-Chainer> <Code-PyTorch> <Paper1> <Paper2> <Slides1> <Slides2>
  143. Deep Joint Task Learning for Generic Object Extraction-2014 <Project> <Code-Caffe> <Dataset> <Paper>
  144. Highly Efficient Forward and Backward Propagation of Convolutional Neural Networks for Pixelwise Classification-2014 <Code-Caffe> <Paper>

2. Panoptic Segmentation

  1. UPSNet: A Unified Panoptic Segmentation Network - CVPR2019 <Paper>
  2. An End-to-end Network for Panoptic Segmentation - Face++ - CVPR2019 [<Paper>]()
  3. Attention-guided Unified Network for Panoptic Segmentation - CVPR2019 <Paper>
  4. Single Network Panoptic Segmentation for Street Scene Understanding - 2019 <Paper>
  5. Panoptic Feature Pyramid Networks - CVPR2019 <Paper>
  6. DeeperLab: Single-Shot Image Parser - 2019 <Paper>
  7. Panoptic Segmentation with a Joint Semantic and Instance Segmentation Network - 2019 <Paper>
  8. Weakly- and Semi-Supervised Panoptic Segmentation - ECCV2018 <Paper> <Code-Matlab> <Project> <Poster>
  9. Panoptic Segmentation - FAIR2018(CVPR2019) <Paper> <Paper-CVPR2019>

3. Human Parsing

  1. Graphonomy: Universal Human Parsing via Graph Transfer Learning - CVPR2019 <Paper> <Code-PyTorch>
  2. Macro-Micro Adversarial Network for Human Parsing - ECCV2018 <Paper> <Code-PyTorch>
  3. Holistic, Instance-level Human Parsing - 2017 <Paper>
  4. Semi-Supervised Hierarchical Semantic Object Parsing - 2017 <Paper>
  5. Towards Real World Human Parsing: Multiple-Human Parsing in the Wild - 2017 <Paper>
  6. Look into Person: Self-supervised Structure-sensitive Learning and A New Benchmark for Human Parsing-2017 <Project> <Code-Caffe> <Paper>
  7. Efficient and Robust Deep Networks for Semantic Segmentation - 2017 <Paper> <Project> <Code-Caffe>
  8. Deep Learning for Human Part Discovery in Images-2016 <Code-Chainer> <Paper>
  9. A CNN Cascade for Landmark Guided Semantic Part Segmentation-2016 <Project> <Paper>
  10. Deep Learning for Semantic Part Segmentation With High-level Guidance-2015 <Paper>
  11. Neural Activation Constellations-Unsupervised Part Model Discovery with Convolutional Networks-2015 <Paper>
  12. Human Parsing with Contextualized Convolutional Neural Network-2015 <Paper>
  13. Part detector discovery in deep convolutional neural networks-2014 <Code-Matlab> <Paper>

4. Clothes Parsing

  1. Looking at Outfit to Parse Clothing-2017 <Paper>
  2. Semantic Object Parsing with Local-Global Long Short-Term Memory-2015 <Paper>
  3. A High Performance CRF Model for Clothes Parsing-2014 <Project> <Code-Matlab> <Dataset> <Paper>
  4. Clothing co-parsing by joint image segmentation and labeling-2013 <Project> <Dataset> <Paper>
  5. Parsing clothing in fashion photographs-2012 <Project> <Paper>

5. Instance Segmentation

  1. YOLACT: Real-time Instance Segmentation - 2019 <Paper> <Code-PyTorch>
  2. Pose2Seg: Detection Free Human Instance Segmentation - CVPR2019 <Paper> <Code-PyTorch> <Project> <Dataset>
  3. Mask Scoring R-CNN - CVPR2019 <Paper> <Code-PyTorch>
  4. Actor-Critic Instance Segmentation - CVPR2019 <Paper>
  5. TensorMask: A Foundation for Dense Object Segmentation - FAIR <Paper>
  6. A Pyramid CNN for Dense-Leaves Segmentation - 2018 <Paper>
  7. Predicting Future Instance Segmentations by Forecasting Convolutional Features - 2018 <Paper>
  8. Path Aggregation Network for Instance Segmentation - CVPR2018 <Paper> <Code-PyTorch>
  9. PixelLink: Detecting Scene Text via Instance Segmentation - AAAI2018 <Code-Tensorflow> <Paper>
  10. MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Features - 2017 - google <Paper>
  11. Recurrent Neural Networks for Semantic Instance Segmentation-2017 <Paper>
  12. Pixelwise Instance Segmentation with a Dynamically Instantiated Network-2017 <Paper>
  13. Semantic Instance Segmentation via Deep Metric Learning-2017 <Paper>
  14. Mask R-CNN-2017 <Code-Tensorflow> <Paper> <Code-Caffe2> <Code-Karas> <Code-PyTorch> <Code-MXNet>
  15. Pose2Seg: Human Instance Segmentation Without Detection - 2018 <Paper>
  16. Pose2Instance: Harnessing Keypoints for Person Instance Segmentation-2017 <Paper>
  17. Pixelwise Instance Segmentation with a Dynamically Instantiated Network-2017 <Paper>
  18. Semantic Instance Segmentation with a Discriminative Loss Function-2017 <Paper>
  19. Fully Convolutional Instance-aware Semantic Segmentation-2016 <Code-MXNet> <Paper>
  20. End-to-End Instance Segmentation with Recurrent Attention <Paper> <Code-Tensorflow>
  21. Instance-aware Semantic Segmentation via Multi-task Network Cascades-2015 <Code-Caffe> <Paper>
  22. Recurrent Instance Segmentation-2015 <Project> <Code-Torch7> <Paper> <Poster> <Video>

6. Segment Object Candidates

  1. Contextual Encoder-Decoder Network for Visual Saliency Prediction - 2019 <Paper>
  2. FastMask: Segment Object Multi-scale Candidates in One Shot-2016 <Code-Caffe> <Paper>
  3. Learning to Refine Object Segments-2016 <Code-Torch> <Paper>
  4. Learning to Segment Object Candidates-2015 <Code-Torch> <Code-Theano-Keras> <Paper>

7. Foreground Object Segmentation

  1. Pixel Objectness-2017 <Project> <Code-Caffe> <Paper>
  2. A Deep Convolutional Neural Network for Background Subtraction-2017 <Paper>
Last modification:July 17th, 2019 at 08:59 am

34 comments

  1. 咸鱼

    博主有没有关注过图卷积网络结合语义分割的?

    1. AIHGF
      @咸鱼

      近期没太关注图卷积网络

  2. yy9199

    请问博主这里面的代码有复现的吗?有没有推荐?比如说哪个报错比较好解决的,哪个 环境满足了基本不报错的

    1. AIHGF
      @yy9199

      很多都容易复现的,比如 FCN、DeepLab、UNet、Mask R-CNN 等经典的

      1. yy9199
        @AIHGF

        好的,谢谢

  3. jay

    请问有目标检测相关论文阅读的栏目吗

  4. 卡卡
    1. 搬仓~
      @卡卡

      第二个网站,程序里边下载模型,是在网址上下载的,然后一直报错Command '['python', 'Seg_utils/get_pretrained_checkpoints.py', '--model=ResNet101']' returned non-zero exit status 1.

    2. 搬仓~
      @卡卡

      我找了好久,前几天进了这个网站,但是运行的时候出了问题,可以qq联系一下吗?714005018求大神指导!

    3. yy9199
      @卡卡

      请问你这些代码合集运行的时候 需要把全部数据集下载好吗?会不会每个net需要的库不一样,运行不同的代码需要下载不同的库?这些NET有运行顺序吗?

      1. AIHGF
        @yy9199

        可以了解下 python 使用不同的库,如虚拟环境

    4. 卡卡
    5. AIHGF
      @卡卡

      感谢!

      1. 卡卡
        @AIHGF

        共同学习,谢谢博主的博客,很赞!

        1. AIHGF
          @卡卡

          多谢多谢. 一点一点的积累.

  5. leexf

    BiSeNet的作者changqianyu在他的repo https://github.com/ycszen/TorchSeg 里实现了BiSeNet

    1. AIHGF
      @leexf

      非常感谢,已添加.

  6. MasterQ

    博主真棒啊,跟着博主这篇博文省了不少找论文的时间,写毕业论文全靠博主的这篇博客了!
    OωO

    1. AIHGF
      @MasterQ

      非常荣幸能有稍许帮助,欢迎互相交流学习.

      1. 咆哮的阿杰
        @AIHGF

        博主有CSDN吗,能加个qq吗 我的qq是 312358434

        1. AIHGF
          @咆哮的阿杰

          2258922522, CSDN 只是备用了.

  7. 小恐龙不会飞

    想请教一下,想识别脸上的眼镜口罩遮挡物应该看哪方面的呢(╹◡╹人)谢谢你

    1. AIHGF
      @小恐龙不会飞

      如果只是检测出眼镜口罩等物体,用目标检测 box 就可以.如果更细致的,语义分割可以.

  8. nana

    博主好厉害,想请教博主关于场景的分割现在常用效果较好且代码公开的算法有哪些,最好是python语言的,谢谢博主!OωO

    1. AIHGF
      @nana

      场景分割经典入门应该有 PSPNet 和 DeepLab 系列的吧,PSPNet 是基于 Caffe 的,tensorflow 提供了 Deeplab 分割的.

  9. 博主厉害,博主有交流群吗?

    1. AIHGF

      没有,就是个人记录备忘

  10. earhian

    谢谢博主,学习了

  11. 博主很厉害,博主下次什么时候更新呢?

    1. AIHGF

      如果你看到相关的,非常欢迎随时通知我,交流学习.

    2. AIHGF

      不定期更新,看到相关的就会更新下

  12. 御宅暴君

    令人感到窒息的密集数量。

  13. 博主好厉害 :smile: :smile:

  14. 谢谢博主 :biggrin:

Leave a Comment