Skip to content

Latest commit

 

History

History
55 lines (32 loc) · 2.39 KB

Segmentation.md

File metadata and controls

55 lines (32 loc) · 2.39 KB

一、语义分割

  1. [FCN] Fully Convolutional Networks for Semantic Segmentation [CVPR' 15]

  2. [SegNet] A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation [TPAMI' 17]

  3. [DeconvNet] Learning Deconvolution Network for Semantic Segmentation

  4. [ENet] A Deep Neural Network Architecture for Real-Time Semantic Segmentation

  5. UNet系列

    • [U-Net] U-Net: Convolutional Networks for Biomedical Image Segmentation [MICCAI' 15]
    • [U-Net++] UNet++: A Nested U-Net Architecture for Medical Image Segmentation [DLMIA' 18]

  6. Deeplab系列

    • [DeeplabV1] Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
    • [DeepLabV2] DeepLab-v2: Semantic Image Segmentation
    • [DeepLabV3] Rethinking Atrous Convolution for Semantic Image Segmentation
    • [DeepLabV3+] Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

  7. [PSPNet] Pyramid Scene Parsing Network [CVPR' 17]

  8. [RefineNet] RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation [CVPR' 17]

  9. Large Kernel Matters–Improve Semantic Segmentation by Global Convolutional Network [ICCV' 17]

  10. [CCNet] CCNet: Criss-Cross Attention for Semantic Segmentation [ICCV' 19]

  11. [BiSeNet] BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation [ECCV' 18]

  12. [ICNet] ICNet for Real-Time Semantic Segmentation on High-Resolution Images [ECCV' 18]

  13. Graph-guided Architecture Search for Real-time Semantic Segmentation

二、实例分割

  1. [Mask R-CNN] Mask R-CNN [ICCV' 17]

  2. [PANet] Path Aggregation Network for Instance Segmentation [CVPR' 18]

  3. [HTC] Hybrid Task Cascade for Instance Segmentation [CVPR' 19]

  4. [MS R-CNN] Mask Scoring R-CNN [CVPR' 19]

  5. Learning to Segment Every Thing [CVPR' 18]

  6. TensorMask: A Foundation for Dense Object Segmentation

三、全景分割

  1. [UPSNet] UPSNet: A Unified Panoptic Segmentation Network [CVPR' 19]

四、部件分割

  1. [CE2P] Devil in the Details: Towards Accurate Single and Multiple Human Parsing
  2. [ACE2P] Augmented Context Embedding with Edge Perceiving