Semantic Segmentation Modules
Channel-wise Cross Fusion Transformer
Introduced by Wang et al. in UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-wise Perspective with TransformerChannel-wise Cross Fusion Transformer is a module used in the UCTransNet architecture for semantic segmentation. It fuses the multi-scale encoder features with the advantage of the long dependency modeling in the Transformer. The CCT module consists of three steps: multi-scale feature embedding, multi-head channel-wise cross attention and Multi-Layer Perceptron (MLP).
Source: UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-wise Perspective with Transformer
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Image Segmentation | 4 | 26.67% |
| Medical Image Segmentation | 4 | 26.67% |
| Semantic Segmentation | 4 | 26.67% |
| Pseudo Label | 1 | 6.67% |
| text annotation | 1 | 6.67% |
| UNET Segmentation | 1 | 6.67% |
Dense Connections
Instance Normalization
Layer Normalization
Multi-Head Attention
Scaled Dot-Product Attention
