Cell image segmentation by Feature Random Enhancement Module
This work addresses a specific training bottleneck in cell image segmentation, offering an incremental improvement for biomedical imaging applications.
The paper tackled the problem of training far layers in deep neural networks for semantic segmentation by proposing a Feature Random Enhancement Module that randomly enhances features during training, improving segmentation accuracy on two cell image datasets without increasing computational cost.
It is important to extract good features using an encoder to realize semantic segmentation with high accuracy. Although loss function is optimized in training deep neural network, far layers from the layers for computing loss function are difficult to train. Skip connection is effective for this problem but there are still far layers from the loss function. In this paper, we propose the Feature Random Enhancement Module which enhances the features randomly in only training. By emphasizing the features at far layers from loss function, we can train those layers well and the accuracy was improved. In experiments, we evaluated the proposed module on two kinds of cell image datasets, and our module improved the segmentation accuracy without increasing computational cost in test phase.