- TL;DR: Proposed method for Cell Image Segmentation
- Reviews Visibility: The authors agree that reviews are made publicly visible, if the submission is accepted.
- Abstract: In order to perform semantic segmentation with high accuracy, it is important to extract good features using an encoder. 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 even if we use skip connection. In this paper, we propose the Feature Random Enhancement Module which enhances the features only in training. By emphasizing the features at far layers from loss function, we can train those layers works 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.
- Keywords: cell image, Semantic Segmentation, U-Net