语义分割 - Semantic Segmentation Papers

最新推荐文章于 2023-08-26 20:24:41 发布
最新推荐文章于 2023-08-26 20:24:41 发布
阅读量1.3k 收藏 6
点赞数 1
分类专栏： 算法

Semantic Segmentation

  1. TernausNet: U-Net with VGG11 Encoder Pre-Trained on ImageNet for Image Segmentation - 2018 - Kaggle [Paper] [Code-PyTorch] [Kaggle-Carvana Image Masking Challenge]
  2. Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation - 2018 - Google [Paper]
  3. End-to-end Detection-Segmentation Network With ROI Convolution - 2018 [Paper]
  4. Mix-and-Match Tuning for Self-Supervised Semantic Segmentation - 2017 [Project] [Paper] [Code-Caffe]
  5. Learning to Segment Every Thing-2017 [Paper] [Code-Caffe2]
  6. Deep Dual Learning for Semantic Image Segmentation-2017 [Paper]
  7. Scene Parsing with Global Context Embedding - 2017 - ICCV [Paper]
  8. FoveaNet: Perspective-aware Urban Scene Parsing - 2017 - ICCV [Paper]
  9. Segmentation-Aware Convolutional Networks Using Local Attention Masks - 2017 [Paper] [Code-Caffe] [Project]
  10. Stacked Deconvolutional Network for Semantic Segmentation-2017 [Paper]
  11. BlitzNet: A Real-Time Deep Network for Scene Understanding-2017 [Project] [Code-Tensorflow] [Paper]
  12. Efficient Yet Deep Convolutional Neural Networks for Semantic Segmentation -2017 [Paper] [Code-Caffe]
  13. LinkNet: Exploiting Encoder Representations for Efficient Semantic Segmentation - 2017 [Paper] [Code-Torch]
  14. Rethinking Atrous Convolution for Semantic Image Segmentation-2017(DeeplabV3) [Paper]
  15. Learning Object Interactions and Descriptions for Semantic Image Segmentation-2017 [Paper]
  16. Pixel Deconvolutional Networks-2017 [Code-Tensorflow] [Paper]
  17. Dilated Residual Networks-2017 [Paper] [Code-PyTorch]
  18. A Review on Deep Learning Techniques Applied to Semantic Segmentation-2017 [Paper]
  19. BiSeg: Simultaneous Instance Segmentation and Semantic Segmentation with Fully Convolutional Networks [Paper]
  20. Efficient ConvNet for Real-time Semantic Segmentation - 2017 [Paper]
  21. ICNet for Real-Time Semantic Segmentation on High-Resolution Images-2017 [Project] [Code] [Paper] [Video]
  22. Not All Pixels Are Equal: Difficulty-Aware Semantic Segmentation via Deep Layer Cascade-2017 [Paper] [Poster] [Project]
  23. Loss Max-Pooling for Semantic Image Segmentation-2017 [Paper]
  24. Annotating Object Instances with a Polygon-RNN-2017 [Project] [Paper]
  25. Feature Forwarding: Exploiting Encoder Representations for Efficient Semantic Segmentation-2017 [Project] [Code-Torch7]
  26. Reformulating Level Sets as Deep Recurrent Neural Network Approach to Semantic Segmentation-2017 [Paper]
  27. Adversarial Examples for Semantic Image Segmentation-2017 [Paper]
  28. Large Kernel Matters - Improve Semantic Segmentation by Global Convolutional Network-2017 [Paper]
  29. Label Refinement Network for Coarse-to-Fine Semantic Segmentation-2017 [Paper]
  30. PixelNet: Representation of the pixels, by the pixels, and for the pixels-2017 [Project] [Code-Caffe] [Paper]
  31. LabelBank: Revisiting Global Perspectives for Semantic Segmentation-2017 [Paper]
  32. Progressively Diffused Networks for Semantic Image Segmentation-2017 [Paper]
  33. Understanding Convolution for Semantic Segmentation-2017 [Model-Mxnet] [Mxnet-Code] [Paper]
  34. Predicting Deeper into the Future of Semantic Segmentation-2017 [Paper]
  35. Pyramid Scene Parsing Network-2017 [Project] [Code-Caffe] [Paper] [Slides]
  36. FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation-2016 [Paper]
  37. FusionNet: A deep fully residual convolutional neural network for image segmentation in connectomics-2016 [Code-PyTorch] [Paper]
  38. RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation-2016 [Code-MatConvNet] [Paper]
  39. Learning from Weak and Noisy Labels for Semantic Segmentation - 2017 [Paper]
  40. The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation [Code-Theano] [Code-Keras1] [Code-Keras2] [Paper]
  41. Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes [Code-Theano] [Paper]
  42. PixelNet: Towards a General Pixel-level Architecture-2016 [Paper]
  43. Recalling Holistic Information for Semantic Segmentation-2016 [Paper]
  44. Semantic Segmentation using Adversarial Networks-2016 [Paper] [Code-Chainer]
  45. Region-based semantic segmentation with end-to-end training-2016 [Paper]
  46. Exploring Context with Deep Structured models for Semantic Segmentation-2016 [Paper]
  47. Better Image Segmentation by Exploiting Dense Semantic Predictions-2016 [Paper]
  48. Boundary-aware Instance Segmentation-2016 [Paper]
  49. Improving Fully Convolution Network for Semantic Segmentation-2016 [Paper]
  50. Deep Structured Features for Semantic Segmentation-2016 [Paper]
  51. DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs-2016 [Project] [Code-Caffe] [Code-Tensorflow] [Code-PyTorch] [Paper]
  52. DeepLab: Semantic Image Segmentation With Deep Convolutional Nets and Fully Connected CRFs-2014 [Code-Caffe1] [Code-Caffe2] [Paper]
  53. Deep Learning Markov Random Field for Semantic Segmentation-2016 [Project] [Paper]
  54. Convolutional Random Walk Networks for Semantic Image Segmentation-2016 [Paper]
  55. ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation-2016 [Code-Caffe1][Code-Caffe2] [Paper] [Blog]
  56. High-performance Semantic Segmentation Using Very Deep Fully Convolutional Networks-2016 [Paper]
  57. ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation-2016 [Paper]
  58. Object Boundary Guided Semantic Segmentation-2016 [Code-Caffe] [Paper]
  59. Segmentation from Natural Language Expressions-2016 [Project] [Code-Tensorflow] [Code-Caffe] [Paper]
  60. Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation-2016 [Code-Caffe] [Paper]
  61. Global Deconvolutional Networks for Semantic Segmentation-2016 [Paper] [Code-Caffe]
  62. Learning Transferrable Knowledge for Semantic Segmentation with Deep Convolutional Neural Network-2015 [Project] [Code-Caffe] [Paper]
  63. Learning Dense Convolutional Embeddings for Semantic Segmentation-2015 [Paper]
  64. ParseNet: Looking Wider to See Better-2015 [Code-Caffe] [Model-Caffe] [Paper]
  65. Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation-2015 [Project] [Code-Caffe] [Paper]
  66. SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation-2015 [Project] [Code-Caffe] [Paper] [Tutorial1] [Tutorial2]
  67. SegNet: A Deep Convolutional Encoder-Decoder Architecture for Robust Semantic Pixel-Wise Labelling-2015 [Code-Caffe] [Code-Chainer] [Paper]
  68. Semantic Image Segmentation with Task-Specific Edge Detection Using CNNs and a Discriminatively Trained Domain Transform-2015 [Paper]
  69. Semantic Segmentation with Boundary Neural Fields-2015 [Code] [Paper]
  70. Semantic Image Segmentation via Deep Parsing Network-2015 [Project] [Paper1] [Paper2] [Slides]
  71. What’s the Point: Semantic Segmentation with Point Supervision-2015 [Project] [Code-Caffe] [Model-Caffe] [Paper]
  72. U-Net: Convolutional Networks for Biomedical Image Segmentation-2015 [Project] [Code+Data] [Code-Keras] [Code-Tensorflow] [Paper] [Notes]
  73. Learning Deconvolution Network for Semantic Segmentation(DeconvNet)-2015 [Project] [Code-Caffe] [Paper] [Slides]
  74. Multi-scale Context Aggregation by Dilated Convolutions-2015 [Project] [Code-Caffe] [Code-Keras] [Paper] [Notes]
  75. ReSeg: A Recurrent Neural Network-based Model for Semantic Segmentation-2015 [Code-Theano] [Paper]
  76. BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation-2015 [Paper]
  77. Feedforward semantic segmentation with zoom-out features-2015 [Code] [Paper] [Video]
  78. Conditional Random Fields as Recurrent Neural Networks-2015 [Project] [Code-Caffe1] [Code-Caffe2] [Demo] [Paper1] [Paper2]
  79. Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation-2015 [Paper]
  80. Fully Convolutional Networks for Semantic Segmentation-2015 [Code-Caffe] [Model-Caffe] [Code-Tensorflow1] [Code-Tensorflow2] [Code-Chainer] [Code-PyTorch] [Paper1] [Paper2] [Slides1] [Slides2]
  81. Deep Joint Task Learning for Generic Object Extraction-2014 [Project] [Code-Caffe] [Dataset] [Paper]
  82. Highly Efficient Forward and Backward Propagation of Convolutional Neural Networks for Pixelwise Classification-2014 [Code-Caffe] [Paper]

Panoptic Segmentation

  1. Panoptic Segmentation - 2018 [Paper]

Human Parsing

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

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] [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]

Instance Segmentation

  1. PixelLink: Detecting Scene Text via Instance Segmentation - 2018 [Paper]
  2. MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Features - 2017 - google [Paper]
  3. Recurrent Neural Networks for Semantic Instance Segmentation-2017 [Paper]
  4. Pixelwise Instance Segmentation with a Dynamically Instantiated Network-2017 [Paper]
  5. Semantic Instance Segmentation via Deep Metric Learning-2017 [Paper]
  6. Mask R-CNN-2017 [Code-Tensorflow] [Paper] [Code-Caffe2]
  7. Pose2Instance: Harnessing Keypoints for Person Instance Segmentation-2017 [Paper]
  8. Pixelwise Instance Segmentation with a Dynamically Instantiated Network-2017 [Paper]
  9. Semantic Instance Segmentation with a Discriminative Loss Function-2017 [Paper]
  10. Fully Convolutional Instance-aware Semantic Segmentation-2016 [Code] [Paper]
  11. End-to-End Instance Segmentation with Recurrent Attention [Paper] [Code-Tensorflow]
  12. Instance-aware Semantic Segmentation via Multi-task Network Cascades-2015 [Code] [Paper]
  13. Recurrent Instance Segmentation-2015 [Project] [Code-Torch7] [Paper] [Poster] [Video]

Segment Object Candidates

  1. FastMask: Segment Object Multi-scale Candidates in One Shot-2016 [Code-Caffe] [Paper]
  2. Learning to Refine Object Segments-2016 [Code-Torch] [Paper]
  3. Learning to Segment Object Candidates-2015 [Code-Torch] [Code-Theano-Keras] [Paper]

Foreground Object Segmentation

  1. Pixel Objectness-2017 [Project] [Code-Caffe] [Paper]
  2. A Deep Convolutional Neural Network for Background Subtraction-2017 
gqixl
关注
  • 1
    点赞
  • 踩
  • 6
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
专栏目录
AI换脸原理(7)——人脸分割参考文献TernausNet: 源码解析
lyy的博客
05-08 182
这篇论文相对来说比较简单，整体是通过使用预训练的权重来提高U-Net的性能，实现对UNet的改进。该方法也是DeepFaceLab官方使用的人脸分割方法。在介绍篇我们已经讲过了UNet的网络结构和设计，在进一步深入了解TernausNet之前，我们先简单回顾下UNet。U-Net的主要结构包括编码器、解码器和瓶颈层三个部分。编码器用于下采样和特征提取，由多个卷积层、ReLU激活函数和最大池化层组成。每次下采样后，输出特征图的尺寸减半，通道数翻倍。
探索TernausNet：高效视觉计算的新篇章
最新发布
gitblog_00099的博客
04-09 238
探索TernausNet：高效视觉计算的新篇章 项目地址:https://gitcode.com/ternaus/TernausNet TernausNet 是一个开源深度学习模型，由Ternaus团队开发，专注于提供高效率和高性能的计算机视觉解决方案。在这个项目中，开发者们已经构建了一系列预训练模型，涵盖了图像分类、对象检测和语义分割等多种任务，使得广大AI开发者可以更轻松地在各种场景下应用深度...
End-to-end detection-segmentation network with ROI convolution
wydbyxr的博客
11-29 288
End-to-end detection-segmentation network with ROI convolution
【论文阅读笔记】ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
qq_44653420的博客
08-26 144
【论文阅读笔记】ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
MaskLab-实例分割（使用语义分割和方向特征精细化目标检测）
mjl_cv的博客
01-02 943
MaskLab-实例分割（使用语义分割和方向特征精细化目标检测） MaskLab: Instance Segmentation by Refining Object Detection with Semanticand Direction Features　　这是一篇2018年cvpr关于实例分割的网络模型，模型主要有三个输出：边界框、语义分割、...
Few-Shot-Semantic-Segmentation-Papers:少量镜头语义分割论文
04-09
少量镜头语义分割论文 注意：如果您的论文不在清单中，请随意或给我。 2021年 标题 会场 PDF格式 代码 少量分割的自适应原型学习和分配 心肺复苏术 自我指导和交叉指导学习，用于少量分割 心肺复苏术 没有元学习的...
segmentation papers
11-17
5. **Fully convolutional networks for semantic segmentation**：由Long等人在2015年的论文中提出，是最早将全卷积网络用于语义分割的工作之一，它结束了传统方法中先进行物体检测再进行分割的步骤，直接对整个...
segmentation papers in deep learning
01-17
4. **Fully Convolutional Instance-aware Semantic Segmentation**：该研究进一步深化了实例分割的概念，旨在同时进行语义分割和实例分割，使得每个像素都包含类别和实例信息。 5. **3D CNN with fully connected ...
Python-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
08-11
Papers and Benchmarks about semantic segmentation, instance segmentation, panoptic segmentation and video segmentation
Python-TernausNet带有VGG11编码器的UNet在ImageNet上预训练用于图像分割
08-11
TernausNet: 带有VGG11编码器的U-Net在ImageNet上预训练，用于图像分割
ENet: A deep neural network architecture for real-time semantic segmentation
liguandong
03-15 1144
ENet: A deep neural network architecture for real-time semantic segmentation Abstract: 18x faster,75x less flops,79x less param 卷积Param: 0.37m 模型参数： 0.7m 卷积参数和模型参数是不一样的 1.Introduction 为了减少内核...
[SDN]Stacked Deconvolutional Network for Semantic Segmentation
Jinming Su
02-05 1168
Abstract 暂时还放在arxiv上，没有出版.中科院自动化所模式匹配国重的文章. 在本文看来，语义分割存在的主要问题是分辨率的降低导致物体细节和小物体损失，现在的很多方法都是致力于如何更好提高分辨率.本文于是提出了Stackecd Deconvolutional Network(SDN) Module来使用逐一堆叠的结构来集成上下文信息，更好地回复局部信息。 Introduct...
论文阅读：《Rethinking BiSeNet For Real-time Semantic Segmentation》
yuansiming0920的博客
05-12 2704
论文链接：https://arxiv.org/pdf/2104.13188.pdf CVPR 2021 1 Background 2 Movtivtion
Semantic Segmentation: A thorough Review
qiusuoxiaozi的博客
03-15 1132
语义分割可以划分到目标检测领域，不同的是，一般意义上目标检测只需要输出被检测物体的bounding box，而语义分割则需要输出一个mask，所以要求更高了。 从技术上说，语义分割归根结底就是对context information的建模。 研究意义 语义分割（Semantic Segmentation）的目标是给定一张图片，对于图片中的每一个像素做分类。例如下中给出的原始输入图片，语义...
论文阅读-《BlitzNet: A Real-Time Deep Network for Scene Understanding》
yj_isee的博客
08-15 3267
ICCV 20171.Motivation:为了做到实时的目标检测和语义分割 2.Framework 采用的是Resnet50+SSD, ssd这种one-stage的检测器天生适合和分割一块做。上采样过程用到的block如下图所示，除了正常的skip connection之外，还用上了residual connection 3.Experiments作者在VOC2007/2012以及COCO
Fast Semantic Segmentation for Scene Perception
qq_41997237的博客
11-13 210
Abstract: 当前大部分的语义分割方法关注精度，而不是效率。本文提出了一种更有 efficient 的神经网络结构，有更少的参数。模型是基于 Resnet 的不对称编解码结构。 在编码器的第一阶段，使用 continuous factorized block 提取 low-level features。 第二阶段使用连续的 dilated block，确保模型有更大的感受野，保持模型 small-scale and shallow。 The parametersof our model are onl
【阅读笔记】《ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation》
ShuqiaoS的博客
04-17 2346
本文记录了博主阅读论文《ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation》的笔记，代码。更新于2019.04.16。
hrnet-semantic-segmentation-hrnet-ocr
05-15
HRNet 是一种深度学习网络结构，可以用于图像语义分割和光学字符识别两个任务。对于图像语义分割，HRNet 利用多尺度特征融合的方法来提升分割精度，同时采用“高分辨率”策略，使得高分辨率特征可以不断通过网络进行...

“相关推荐”对你有帮助么？

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值