MSGDD-cGAN: Multi-Scale Gradients Dual Discriminator Conditional Generative Adversarial Network

TL;DR

This paper introduces MSGDD-cGAN, a novel multi-scale gradient dual discriminator cGAN that stabilizes training and improves output quality, demonstrated by enhanced fetal ultrasound image segmentation performance.

Contribution

It proposes a new architecture combining multi-scale gradient flow and dual discrimination to stabilize training and balance input-output correlation in cGANs.

Findings

3.18% increase in F1 score over pix2pix cGANs

Enhanced stability in training cGANs

Improved segmentation accuracy for fetal ultrasound images

Abstract

Conditional Generative Adversarial Networks (cGANs) have been used in many image processing tasks. However, they still have serious problems maintaining the balance between conditioning the output on the input and creating the output with the desired distribution based on the corresponding ground truth. The traditional cGANs, similar to most conventional GANs, suffer from vanishing gradients, which backpropagate from the discriminator to the generator. Moreover, the traditional cGANs are sensitive to architectural changes due to previously mentioned gradient problems. Therefore, balancing the architecture of the cGANs is almost impossible. Recently MSG-GAN has been proposed to stabilize the performance of the GANs by applying multiple connections between the generator and discriminator. In this work, we propose a method called MSGDD-cGAN, which first stabilizes the performance of the cGANs using multi-connections gradients flow. Secondly, the proposed network architecture balances the correlation of the output to input and the fitness of the output on the target distribution. This balance is generated by using the proposed dual discrimination procedure. We tested our model by segmentation of fetal ultrasound images. Our model shows a 3.18% increase in the F1 score comparing to the pix2pix version of cGANs.