In recent years, there has been a rising interest to incorporate attention into deep learning architectures for biomedical image segmentation. The modular design of attention mechanisms enable flexible integration into convolutional neural network architectures such as the U-Net. Whether attention is appropriate to use, what type of attention to use, and where in the network to incorporate attention modules, are all important considerations that are currently overlooked. In this paper, we investigate the role of the Focal parameter in modulating attention, revealing a link between attention in loss functions and networks. By incorporating a Focal distance penalty term, we extend the Unified Focal loss framework to include boundary-based losses. Furthermore, we develop a simple and interpretable, dataset and model-specific heuristic to integrate the Focal parameter into the Squeeze-and-Excitation block and Attention Gate, achieving the best results with fewer number of attention modules on three well-validated biomedical imaging datasets, suggesting judicious use of attention modules results in better performance and efficiency. The source code is available at: https://github.com/mlyg/focal-attention-networks.
Focal Attention Networks: Optimising Attention for Biomedical Image Segmentation
Rundo L.;
2022-01-01
Abstract
In recent years, there has been a rising interest to incorporate attention into deep learning architectures for biomedical image segmentation. The modular design of attention mechanisms enable flexible integration into convolutional neural network architectures such as the U-Net. Whether attention is appropriate to use, what type of attention to use, and where in the network to incorporate attention modules, are all important considerations that are currently overlooked. In this paper, we investigate the role of the Focal parameter in modulating attention, revealing a link between attention in loss functions and networks. By incorporating a Focal distance penalty term, we extend the Unified Focal loss framework to include boundary-based losses. Furthermore, we develop a simple and interpretable, dataset and model-specific heuristic to integrate the Focal parameter into the Squeeze-and-Excitation block and Attention Gate, achieving the best results with fewer number of attention modules on three well-validated biomedical imaging datasets, suggesting judicious use of attention modules results in better performance and efficiency. The source code is available at: https://github.com/mlyg/focal-attention-networks.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.