English

EyeLoveGAN: Exploiting domain-shifts to boost network learning with cycleGANs

Computer Vision and Pattern Recognition 2022-03-11 v1 Artificial Intelligence

Abstract

This paper presents our contribution to the REFUGE challenge 2020. The challenge consisted of three tasks based on a dataset of retinal images: Segmentation of optic disc and cup, classification of glaucoma, and localization of fovea. We propose employing convolutional neural networks for all three tasks. Segmentation is performed using a U-Net, classification is performed by a pre-trained InceptionV3 network, and fovea detection is performed by employing stacked hour-glass for heatmap prediction. The challenge dataset contains images from three different data sources. To enhance performance, cycleGANs were utilized to create a domain-shift between the data sources. These cycleGANs move images across domains, thus creating artificial images which can be used for training.

Keywords

Cite

@article{arxiv.2203.05344,
  title  = {EyeLoveGAN: Exploiting domain-shifts to boost network learning with cycleGANs},
  author = {Josefine Vilsbøll Sundgaard and Kristine Aavild Juhl and Jakob Mølkjær Slipsager},
  journal= {arXiv preprint arXiv:2203.05344},
  year   = {2022}
}