Semantic Segmentation Models
UCTransNet
Introduced by Wang et al. in UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-wise Perspective with TransformerUCTransNet is an end-to-end deep learning network for semantic segmentation that takes U-Net as the main structure of the network. The original skip connections of U-Net are replaced by CTrans consisting of two components: Channel-wise Cross fusion Transformer (CCT) and Channel-wise Cross Attention (CCA) to guide the fused multi-Scale channel-wise information to effectively connect to the decoder features for eliminating the ambiguity.
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 | 25.00% |
| Medical Image Segmentation | 4 | 25.00% |
| Semantic Segmentation | 4 | 25.00% |
| Pseudo Label | 1 | 6.25% |
| text annotation | 1 | 6.25% |
| Decoder | 1 | 6.25% |
| UNET Segmentation | 1 | 6.25% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
Channel-wise Cross Attention
|
Attention Modules | |
Channel-wise Cross Fusion Transformer
|
Semantic Segmentation Modules |
