SeGANmentation: Segmentation via GAN-Based Image-to-Image Translation
Authors:
Open Access
- 22 September 2026
- journal article
- Published by Universitat Autonoma de Barcelona in ELCVIA Electronic Letters on Computer Vision and Image Analysis
- Vol. 25 (3) , 22-44
Abstract
This research explores the potential of state-of-the-art Generative Adversarial Networks (GANs) for segmentation through image-to-image (I2I) translation. The presented model, seGANmentation, combines convolutional neural networks and vision transformers to generate segmentation labels directly from input images. It aims to reduce manual labeling and enhance segmentation performance using synthetic data. Comparative analysis with U-Net as a benchmark in segmentation, shows U-Net achieving an average of 0.99 in accuracy, Dice Coefficient, and Intersection over Union, while seGANmentation scores 0.90, 0.83, and 0.71, respectively. Although it did not outperform U-Net, it highlights the potential for GAN-based segmentation. This work lays the foundation for employing GANs in this novel approach. This paper's proposed framework could be valuable in data-scarce scenarios, enhance task accuracy with synthetic data augmentation, reduce the need for extensive training pairs by refining GAN-generated labels with off-the-shelf segmentors, and achieve unsupervised segmentation, unlike traditional neural networks. These hypotheses remain to be tested in future studies.Keywords
This publication has 29 references indexed in Scilit:
- Unsupervised many-to-many stain translation for histological image augmentation to improve classification accuracyJournal of Pathology Informatics, 2023
- Multimodal Unsupervised Image-to-Image Translation2018
- Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation2018
- Which Way Round? A Study on the Performance of Stain-Translation for Segmenting Arbitrarily Dyed Histological Images2018
- SegAN: Adversarial Network with Multi-scale L1 Loss for Medical Image SegmentationNeuroinformatics, 2018
- Computer Vision – ECCV 20182018
- Computer Vision – ECCV 20182018
- Medical Image Computing and Computer Assisted Intervention – MICCAI 20182018
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Medical Image Computing and Computer-Assisted Intervention – MICCAI 20152015