Semantic Segmentation Models
DeepLabv2
Introduced by Chen et al. in DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFsDeepLabv2 is an architecture for semantic segmentation that build on DeepLab with an atrous spatial pyramid pooling scheme. Here we have parallel dilated convolutions with different rates applied in the input feature map, which are then fused together. As objects of the same class can have different sizes in the image, ASPP helps to account for different object sizes.
Source: DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Semantic Segmentation | 4 | 40.00% |
| Domain Adaptation | 2 | 20.00% |
| Unsupervised Domain Adaptation | 2 | 20.00% |
| Semi-Supervised Semantic Segmentation | 1 | 10.00% |
| Image Segmentation | 1 | 10.00% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
ASPP
|
Semantic Segmentation Modules | |
CRF
|
Structured Prediction | |
Dilated Convolution
|
Convolutions | |
Feedforward Network
|
Feedforward Networks |
