- FCN:Fully Convolutional Networks for Semantic Segmentation Paper2
- RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation
- PSPNet:Pyramid Scene Parsing Network
- ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
- ICNet for Real-Time Semantic Segmentation on High-Resolution Images
- FC-DenseNet:The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation
- Mobile UNet for Semantic Segmentation
- Encoder-Decoder with skip connections based on SegNet
- Encoder-Decoder based on SegNet
- Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes
The only thing you have to do to get started is set up the folders in the following structure:
├── "dataset_name"
| ├── train
| ├── train_labels
| ├── val
| ├── val_labels
| ├── test
| ├── test_labels