Semantic Segmentation Models
DeepLab
Introduced by Chen et al. in Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFsDeepLab is a semantic segmentation architecture. First, the input image goes through the network with the use of dilated convolutions. Then the output from the network is bilinearly interpolated and goes through the fully connected CRF to fine tune the result we obtain the final predictions.
Source: Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Semantic Segmentation | 38 | 26.21% |
| Image Segmentation | 11 | 7.59% |
| Object Detection | 6 | 4.14% |
| Decoder | 6 | 4.14% |
| Autonomous Vehicles | 5 | 3.45% |
| General Classification | 5 | 3.45% |
| Scene Understanding | 4 | 2.76% |
| Management | 4 | 2.76% |
| Image Classification | 3 | 2.07% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
CRF
|
Structured Prediction | |
Dilated Convolution
|
Convolutions | |
Feedforward Network
|
Feedforward Networks |
