Adversarial Mutual Leakage Network for Cell Image Segmentation

TL;DR

This paper introduces an innovative adversarial network leveraging mutual information leakage between generator and discriminator to enhance cell image segmentation accuracy.

Contribution

It presents three novel segmentation methods using GANs that exploit information leakage for improved training and performance.

Findings

AML-Net significantly outperforms conventional segmentation methods.

Mutual leakage improves training efficiency.

Proposed modules enhance focus on important image features.

Abstract

We propose three segmentation methods using GAN and information leakage between generator and discriminator. First, we propose an Adversarial Training Attention Module (ATA-Module) that uses an attention mechanism from the discriminator to the generator to enhance and leak important information in the discriminator. ATA-Module transmits important information to the generator from the discriminator. Second, we propose a Top-Down Pixel-wise Difficulty Attention Module (Top-Down PDA-Module) that leaks an attention map based on pixel-wise difficulty in the generator to the discriminator. The generator trains to focus on pixel-wise difficulty, and the discriminator uses the difficulty information leaked from the generator for classification. Finally, we propose an Adversarial Mutual Leakage Network (AML-Net) that mutually leaks the information each other between the generator and the discriminator. By using the information of the other network, it is able to train more efficiently than ordinary segmentation models. Three proposed methods have been evaluated on two datasets for cell image segmentation. The experimental results show that the segmentation accuracy of AML-Net was much improved in comparison with conventional methods.