# Revisiting CycleGAN for semi-supervised segmentation

arXiv: https://arxiv.org/abs/1908.11569 · HTML: https://mlsanity.com/paper/1908.11569/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Aug 2019.

## Built on by (most cited first, 6 of 6)

- [Anatomy-XNet: An Anatomy Aware Convolutional Neural Network for Thoracic Disease Classification in Chest X-rays](https://mlsanity.com/paper/2106.05915/) (2021)
- [A-ACT: Action Anticipation through Cycle Transformations](https://mlsanity.com/paper/2204.00942/) (2022)
- [SemiCurv: Semi-Supervised Curvilinear Structure Segmentation](https://mlsanity.com/paper/2205.08706/) (2022)
- [Nucleus-aware Self-supervised Pretraining Using Unpaired Image-to-image Translation for Histopathology Images](https://mlsanity.com/paper/2309.07394/) (2023)
- [Semi-supervised domain adaptation with CycleGAN guided by a downstream task loss](https://mlsanity.com/paper/2208.08815/) (2022)
- [Improving Performance of Semantic Segmentation CycleGANs by Noise Injection into the Latent Segmentation Space](https://mlsanity.com/paper/2201.06415/) (2022)

## Abstract (arXiv)

In this work, we study the problem of training deep networks for semantic image segmentation using only a fraction of annotated images, which may significantly reduce human annotation efforts. Particularly, we propose a strategy that exploits the unpaired image style transfer capabilities of CycleGAN in semi-supervised segmentation. Unlike recent works using adversarial learning for semi-supervised segmentation, we enforce cycle consistency to learn a bidirectional mapping between unpaired images and segmentation masks. This adds an unsupervised regularization effect that boosts the segmentation performance when annotated data is limited. Experiments on three different public segmentation benchmarks (PASCAL VOC 2012, Cityscapes and ACDC) demonstrate the effectiveness of the proposed method. The proposed model achieves 2-4% of improvement with respect to the baseline and outperforms recent approaches for this task, particularly in low labeled data regime.