Semantic Segmentation with CNN
Paper, Code, and Other Resources about Semantic Segmentation.
Semantic Image Segmentation
- Fully Convolutional Network for Semantic Segmentation. CVPR 2015, TPAM I2016 [Paper] [Code]
- DeepLab v1: Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs. ICLR 2015
- CRFasRNN: Conditional Random Fields as Recurrent Neural Networks. ICCV 2015.
- ParseNet: Looking Wider to See Better. ICLR 2016 [Paper][Code]
- DeepLab v2: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs. TPAMI 2017.
- DeepLab v3: Rethinking Atrous Convolution for Semantic Image Segmentation
- DeepLab v3+: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation.
- combine spatial pyramid pooling module and encoder-decoder structure.
- the former one make full use of context info, the latter one get finer boundaries.
- SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation. TPAMI 2017.
- ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation.
- RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation.
- PSPNet: Pyramid Scene Parsing Network.
- ICNet for Real-Time Semantic Segmentation on High-Resolution Images.
- LinkNet: Exploiting Encoder Representations for Efficient Semantic Segmentation
- UNet: Convolutional Networks for Biomedical Image Segmentation
- Not all pixels are equal
- Tiramisu The One Hundered Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation
- spn: learning affinity from spatial propogation network. NIPS2017.
- We propose spattial propagation networks for learning the affinity for vision tasks.
- The model can learn semantically-aware affinity value for high-level vision tasks due to the powerful learning capability of deep CNNs.
- Valide the framework on the task of refinement of image segmentation boundaries. Experiments show that the spatial propagation network provides a general, effictive and efficient solution for generating high-quality segmentation results.
Survey & Review
- A Review on Deep Learning Techniques Applied to Semantic Segmentation
- Real-time semantic segmentation comparative survey.
Semantic Video Segmentation
Specific Segmentation & Applications
- Portrait Segmentation for Image Stylization. EG2016.
- Deep Automatic Matting. CVPR2017.