# Semi-supervised FusedGAN for Conditional Image Generation

arXiv: https://arxiv.org/abs/1801.05551 · HTML: https://mlsanity.com/paper/1801.05551/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jan 2018.

## Built on by (most cited first, 12 of 12)

- [DE-FAKE: Detection and Attribution of Fake Images Generated by Text-to-Image Generation Models](https://mlsanity.com/paper/2210.06998/) (2022)
- [Adversarial Text-to-Image Synthesis: A Review](https://mlsanity.com/paper/2101.09983/) (2021)
- [Multimodal Image Synthesis and Editing: The Generative AI Era](https://mlsanity.com/paper/2112.13592/) (2021)
- [Controllable Data Generation by Deep Learning: A Review](https://mlsanity.com/paper/2207.09542/) (2022)
- [Bi-LORA: A Vision-Language Approach for Synthetic Image Detection](https://mlsanity.com/paper/2404.01959/) (2024)
- [Semi-Supervised Deep Regression with Uncertainty Consistency and Variational Model Ensembling via Bayesian Neural Networks](https://mlsanity.com/paper/2302.07579/) (2023)
- [Deep Image Synthesis from Intuitive User Input: A Review and Perspectives](https://mlsanity.com/paper/2107.04240/) (2021)
- [Interactive Image Manipulation with Complex Text Instructions](https://mlsanity.com/paper/2211.15352/) (2022)
- [Text-to-Image Cross-Modal Generation: A Systematic Review](https://mlsanity.com/paper/2401.11631/) (2024)
- [MixSyn: Learning Composition and Style for Multi-Source Image Synthesis](https://mlsanity.com/paper/2111.12705/) (2021)
- [Transductive Zero-Shot Learning by Decoupled Feature Generation](https://mlsanity.com/paper/2102.03266/) (2021)
- [Accountable Textual-Visual Chat Learns to Reject Human Instructions in Image Re-creation](https://mlsanity.com/paper/2303.05983/) (2023)

## Abstract (arXiv)

We present FusedGAN, a deep network for conditional image synthesis with controllable sampling of diverse images. Fidelity, diversity and controllable sampling are the main quality measures of a good image generation model. Most existing models are insufficient in all three aspects. The FusedGAN can perform controllable sampling of diverse images with very high fidelity. We argue that controllability can be achieved by disentangling the generation process into various stages. In contrast to stacked GANs, where multiple stages of GANs are trained separately with full supervision of labeled intermediate images, the FusedGAN has a single stage pipeline with a built-in stacking of GANs. Unlike existing methods, which requires full supervision with paired conditions and images, the FusedGAN can effectively leverage more abundant images without corresponding conditions in training, to produce more diverse samples with high fidelity. We achieve this by fusing two generators: one for unconditional image generation, and the other for conditional image generation, where the two partly share a common latent space thereby disentangling the generation. We demonstrate the efficacy of the FusedGAN in fine grained image generation tasks such as text-to-image, and attribute-to-face generation.