# ComboGAN: Unrestrained Scalability for Image Domain Translation

arXiv: https://arxiv.org/abs/1712.06909 · HTML: https://mlsanity.com/paper/1712.06909/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Dec 2017.

## Built on by (most cited first, 30 of 37)

- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [Diffusion-based Image Translation using Disentangled Style and Content Representation](https://mlsanity.com/paper/2209.15264/) (2022)
- [Diffusion Models for Image Restoration and Enhancement: A Comprehensive Survey](https://mlsanity.com/paper/2308.09388/) (2023)
- [Model-Based Domain Generalization](https://mlsanity.com/paper/2102.11436/) (2021)
- [Invariant Information Bottleneck for Domain Generalization](https://mlsanity.com/paper/2106.06333/) (2021)
- [Learning to generate line drawings that convey geometry and semantics](https://mlsanity.com/paper/2203.12691/) (2022)
- [Disentangled Cycle Consistency for Highly-realistic Virtual Try-On](https://mlsanity.com/paper/2103.09479/) (2021)
- [Exploring Patch-wise Semantic Relation for Contrastive Learning in Image-to-Image Translation Tasks](https://mlsanity.com/paper/2203.01532/) (2022)
- [Look Closer to Supervise Better: One-Shot Font Generation via Component-Based Discriminator](https://mlsanity.com/paper/2205.00146/) (2022)
- [Beyond Privacy: Navigating the Opportunities and Challenges of Synthetic Data](https://mlsanity.com/paper/2304.03722/) (2023)
- [Rethinking Domain Generalization: Discriminability and Generalizability](https://mlsanity.com/paper/2309.16483/) (2023)
- [Thermal Infrared Image Colorization for Nighttime Driving Scenes with Top-Down Guided Attention](https://mlsanity.com/paper/2104.14374/) (2021)
- [A Unified Hyper-GAN Model for Unpaired Multi-contrast MR Image Translation](https://mlsanity.com/paper/2107.11945/) (2021)
- [What makes visual place recognition easy or hard?](https://mlsanity.com/paper/2106.12671/) (2021)
- [Learning Multi-Site Harmonization of Magnetic Resonance Images Without Traveling Human Phantoms](https://mlsanity.com/paper/2110.00041/) (2021)
- [Let There be Light: Improved Traffic Surveillance via Detail Preserving Night-to-Day Transfer](https://mlsanity.com/paper/2105.05011/) (2021)
- [Diverse Target and Contribution Scheduling for Domain Generalization](https://mlsanity.com/paper/2309.16460/) (2023)
- [Physics-informed Guided Disentanglement in Generative Networks](https://mlsanity.com/paper/2107.14229/) (2021)
- [A Domain Gap Aware Generative Adversarial Network for Multi-domain Image Translation](https://mlsanity.com/paper/2110.10837/) (2021)
- [Learning Class and Domain Augmentations for Single-Source Open-Domain Generalization](https://mlsanity.com/paper/2311.02599/) (2023)
- [Quality Metric Guided Portrait Line Drawing Generation from Unpaired Training Data](https://mlsanity.com/paper/2202.03678/) (2022)
- [Multi-Domain Image-to-Image Translation with Adaptive Inference Graph](https://mlsanity.com/paper/2101.03806/) (2021)
- [Critically examining the Domain Generalizability of Facial Expression Recognition models](https://mlsanity.com/paper/2106.15453/) (2021)
- [Facial Expression Translation using Landmark Guided GANs](https://mlsanity.com/paper/2209.02136/) (2022)
- [SAR2EO: A High-resolution Image Translation Framework with Denoising Enhancement](https://mlsanity.com/paper/2304.04760/) (2023)
- [From Invariant Representations to Invariant Data: Provable Robustness to Spurious Correlations via Noisy Counterfactual Matching](https://mlsanity.com/paper/2505.24843/) (2025)
- [Domain-Scalable Unpaired Image Translation via Latent Space Anchoring](https://mlsanity.com/paper/2306.14879/) (2023)
- [Scalable, Trustworthy Generative Model for Virtual Multi-Staining from H&E Whole Slide Images](https://mlsanity.com/paper/2407.00098/) (2024)
- [Gated SwitchGAN for multi-domain facial image translation](https://mlsanity.com/paper/2111.14096/) (2021)
- [Place Recognition under Occlusion and Changing Appearance via Disentangled Representations](https://mlsanity.com/paper/2211.11439/) (2022)

## Abstract (arXiv)

This year alone has seen unprecedented leaps in the area of learning-based image translation, namely CycleGAN, by Zhu et al. But experiments so far have been tailored to merely two domains at a time, and scaling them to more would require an quadratic number of models to be trained. And with two-domain models taking days to train on current hardware, the number of domains quickly becomes limited by the time and resources required to process them. In this paper, we propose a multi-component image translation model and training scheme which scales linearly - both in resource consumption and time required - with the number of domains. We demonstrate its capabilities on a dataset of paintings by 14 different artists and on images of the four different seasons in the Alps. Note that 14 data groups would need (14 choose 2) = 91 different CycleGAN models: a total of 182 generator/discriminator pairs; whereas our model requires only 14 generator/discriminator pairs.