/Semantic-Segmentation-Review

Semantic Segmentation Paper를 review하고 해당 코드를 구현하는 repository 입니다.

Primary LanguageJupyter NotebookApache License 2.0Apache-2.0

Semantic Segmentation Korean Review

Contributors

풀잎스쿨 15기 Semantic Segmentation 논문으로 입문하기 멤버

  • 김덕주, 김소연, 김현우, 류영표, 박근범, 백장현, 심주용, 이명오, 이영석, 이은경, 이해중

Encoder-Decoder 형식의 Semantic Segmentation

  • Fully Convolutional Networks for semantic Segmentation [paper / reivew]
  • Learning Deconvolution Network for Semantic Segmentation [paper / review]
  • SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation [paper / review]
  • RedNet: Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections [paper / review]
  • LinkNet: Exploiting Encoder Representations for Efficient Semantic Segmentation [paper / review]
  • SDN : Stacked Deconvolutional Network for Semantic Segmentation [paper / review]

U-Net 형식의 Semantic Segmentation

  • U-Net: Convolutional Networks for Biomedical Image Segmentation [paper / review]
  • V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation [paper / review]
  • UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation [paper1, paper2 / review]
  • UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentation [paper / review]
  • Attention U-Net: Learning Where to Look for the Pancreas [paper / review]
  • The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation [paper / review]
  • Eff-UNet: A Novel Architecture for Semantic Segmentation in Unstructured Environment [paper / review]
  • Double-UNet: DoubleU-Net: A Deep Convolutional Neural Network for Medical Image Segmentation [paper / review]

DeepLab 형식의 이용한 Semantic Segmentation

  • Multi-Scale Context Aggregation by Dilated Convolutions [paper / review]
  • DeepLab V1: Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs [paper / review]
  • DeepLab V2: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs [paper / review]
  • DeepLab V3: Rethinking Atrous Convolution for Semantic Image Segmentation [paper / review]
  • DeepLab V3+: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation [paper / review]

Receptive Field의 한계를 극복하려고 시도한 Semantic Segmentation

  • Pyramid Scene Parsing Network [paper / review]
  • Deformable Convolutional Networks [paper / review]
  • Large Kernel Matters - Improve Semantic Segmentation by Global Convolutional Network [paper / review]

High Resolution을 복원하려는 논문

  • HRNet : Deep High-Resolution Representation Learning for Visual Recognition [paper / review]

Competition paper

[ECCV 2020 Workshop]

  • Summary [pdf]
  • 1st : Multi-level tail pixel cutmix and scale attention for long-tailed scene parsing [paper]
  • 2nd : Diversification is All You Need: Towards Data Efficient Image Understanding [paper]
  • 3rd : Edge-Preserving Guided Semantic Segmentation for VIPriors Challenge [paper]
  • 4th : EfficientSeg: An Efficient Semantic Segmentation Network [paper]
  • 5th : Data-efficient semantic segmentation via extremely perturbed data augmentation [paper]
  • other : Hoya's segmentation_tutorial_pytorch [paper / code]

[SIIM-ACR Pneumothorax Segmentation]

  • Summary [pdf]

[Severstal Steel Defect Detection]

  • Summary [pdf]

[Kaggle Summary Poster]