Semantic Segmentation Models
EfficientUNet++
Introduced by Silva et al. in Encoder-Decoder Architectures for Clinically Relevant Coronary Artery SegmentationDecoder architecture inspired on the UNet++ structure and the EfficientNet building blocks. Keeping the UNet++ structure, the EfficientUNet++ achieves higher performance and significantly lower computational complexity through two simple modifications:
- Replaces the 3x3 convolutions of the UNet++ with residual bottleneck blocks with depthwise convolutions
- Applies channel and spatial attention to the bottleneck feature maps using concurrent spatial and channel squeeze & excitation (scSE) blocks
Papers
| Paper | Code | Results | Date | Stars |
|---|
Concurrent Spatial and Channel Squeeze & Excitation
Depthwise Convolution
Depthwise Separable Convolution
Pointwise Convolution
