Decoder architecture based on the UNet++. Combining residual bottlenecks with depthwise convolutions and attention mechanisms, it outperforms the UNet++ in a coronary artery segmentation task, while being significantly more computationally efficient.
deep-learning pytorch segmentation unet medical-image-segmentation efficientnet unetplusplus efficientunetplusplus
- Updated
Jan 20, 2022 - Python