# Robust Conditional Generative Adversarial Networks

arXiv: https://arxiv.org/abs/1805.08657 · HTML: https://mlsanity.com/paper/1805.08657/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 May 2018.

## Built on by (most cited first, 8 of 8)

- [Advancements in Generative AI: A Comprehensive Review of GANs, GPT, Autoencoders, Diffusion Model, and Transformers](https://mlsanity.com/paper/2311.10242/) (2023)
- [MedM2G: Unifying Medical Multi-Modal Generation via Cross-Guided Diffusion with Visual Invariant](https://mlsanity.com/paper/2403.04290/) (2024)
- [Visual Text Meets Low-level Vision: A Comprehensive Survey on Visual Text Processing](https://mlsanity.com/paper/2402.03082/) (2024)
- [Few-Shot Learning with Adaptive Weight Masking in Conditional GANs](https://mlsanity.com/paper/2412.03105/) (2024)
- [A Physics-informed machine learning model for time-dependent wave runup prediction](https://mlsanity.com/paper/2401.08684/) (2024)
- [Deterministic World Models for Closed-loop Reachability Analysis of End-to-End Vision-based Control](https://mlsanity.com/paper/2512.08991/) (2025)
- [Learning from Mistakes based on Class Weighting with Application to Neural Architecture Search](https://mlsanity.com/paper/2112.00275/) (2021)
- [DiffuMural: Restoring Dunhuang Murals with Multi-scale Diffusion](https://mlsanity.com/paper/2504.09513/) (2025)

## Abstract (arXiv)

Conditional generative adversarial networks (cGAN) have led to large improvements in the task of conditional image generation, which lies at the heart of computer vision. The major focus so far has been on performance improvement, while there has been little effort in making cGAN more robust to noise. The regression (of the generator) might lead to arbitrarily large errors in the output, which makes cGAN unreliable for real-world applications. In this work, we introduce a novel conditional GAN model, called RoCGAN, which leverages structure in the target space of the model to address the issue. Our model augments the generator with an unsupervised pathway, which promotes the outputs of the generator to span the target manifold even in the presence of intense noise. We prove that RoCGAN share similar theoretical properties as GAN and experimentally verify that our model outperforms existing state-of-the-art cGAN architectures by a large margin in a variety of domains including images from natural scenes and faces.