# ZstGAN: An Adversarial Approach for Unsupervised Zero-Shot Image-to-Image Translation

arXiv: https://arxiv.org/abs/1906.00184 · HTML: https://mlsanity.com/paper/1906.00184/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jun 2019.

## Built on by (most cited first, 9 of 9)

- [Image-to-Image Translation: Methods and Applications](https://mlsanity.com/paper/2101.08629/) (2021)
- [FakeNews: GAN-based generation of realistic 3D volumetric data -- A systematic review and taxonomy](https://mlsanity.com/paper/2207.01390/) (2022)
- [ManiFest: Manifold Deformation for Few-shot Image Translation](https://mlsanity.com/paper/2111.13681/) (2021)
- [Zero-shot-Learning Cross-Modality Data Translation Through Mutual Information Guided Stochastic Diffusion](https://mlsanity.com/paper/2301.13743/) (2023)
- [Leveraging Local Domains for Image-to-Image Translation](https://mlsanity.com/paper/2109.04468/) (2021)
- [ACE: Zero-Shot Image to Image Translation via Pretrained Auto-Contrastive-Encoder](https://mlsanity.com/paper/2302.11705/) (2023)
- [ODIN: On-demand Data Formulation to Mitigate Dataset Lock-in](https://mlsanity.com/paper/2303.06832/) (2023)
- [Controllable retinal image synthesis using conditional StyleGAN and latent space manipulation for improved diagnosis and grading of diabetic retinopathy](https://mlsanity.com/paper/2409.07422/) (2024)
- [Zero-Shot Visual Concept Blending Without Text Guidance](https://mlsanity.com/paper/2503.21277/) (2025)

## Abstract (arXiv)

Image-to-image translation models have shown remarkable ability on transferring images among different domains. Most of existing work follows the setting that the source domain and target domain keep the same at training and inference phases, which cannot be generalized to the scenarios for translating an image from an unseen domain to another unseen domain. In this work, we propose the Unsupervised Zero-Shot Image-to-image Translation (UZSIT) problem, which aims to learn a model that can translate samples from image domains that are not observed during training. Accordingly, we propose a framework called ZstGAN: By introducing an adversarial training scheme, ZstGAN learns to model each domain with domain-specific feature distribution that is semantically consistent on vision and attribute modalities. Then the domain-invariant features are disentangled with an shared encoder for image generation. We carry out extensive experiments on CUB and FLO datasets, and the results demonstrate the effectiveness of proposed method on UZSIT task. Moreover, ZstGAN shows significant accuracy improvements over state-of-the-art zero-shot learning methods on CUB and FLO.