# SIDA: Synthetic Image Driven Zero-shot Domain Adaptation

arXiv: https://arxiv.org/abs/2507.18632 · HTML: https://mlsanity.com/paper/2507.18632/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 31 references that are in the map.
- First posted on arXiv 24 Jul 2025.

## Builds on (most cited first, 20 of 20)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [Playing for Data: Ground Truth from Computer Games](https://mlsanity.com/paper/1608.02192/) (2016)
- [Domain Generalization with MixStyle](https://mlsanity.com/paper/2104.02008/) (2021)
- [Learning to Learn Single Domain Generalization](https://mlsanity.com/paper/2003.13216/) (2020)
- [Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2101.10979/) (2021)
- [CLIPstyler: Image Style Transfer with a Single Text Condition](https://mlsanity.com/paper/2112.00374/) (2021)
- [Patch-Mix Transformer for Unsupervised Domain Adaptation: A Game Perspective](https://mlsanity.com/paper/2303.13434/) (2023)
- [One-shot Unsupervised Domain Adaptation with Personalized Diffusion Models](https://mlsanity.com/paper/2303.18080/) (2023)
- [Unified Language-driven Zero-shot Domain Adaptation](https://mlsanity.com/paper/2404.07155/) (2024)
- [Generalization by Adaptation: Diffusion-Based Domain Extension for Domain-Generalized Semantic Segmentation](https://mlsanity.com/paper/2312.01850/) (2023)
- [IFCap: Image-like Retrieval and Frequency-based Entity Filtering for Zero-shot Captioning](https://mlsanity.com/paper/2409.18046/) (2024)
- [Informative Data Mining for One-Shot Cross-Domain Semantic Segmentation](https://mlsanity.com/paper/2309.14241/) (2023)
- [VerbDiff: Text-Only Diffusion Models with Enhanced Interaction Awareness](https://mlsanity.com/paper/2503.16406/) (2025)
- [ControlUDA: Controllable Diffusion-assisted Unsupervised Domain Adaptation for Cross-Weather Semantic Segmentation](https://mlsanity.com/paper/2402.06446/) (2024)

## Built on by (most cited first, 4 of 4)

- [Fake-HR1: Rethinking Reasoning of Vision Language Model for Synthetic Image Detection](https://mlsanity.com/paper/2602.10042/) (2026)
- [Sali4Vid: Saliency-Aware Video Reweighting and Adaptive Caption Retrieval for Dense Video Captioning](https://mlsanity.com/paper/2509.04602/) (2025)
- [SAIL: Similarity-Aware Guidance and Inter-Caption Augmentation-based Learning for Weakly-Supervised Dense Video Captioning](https://mlsanity.com/paper/2603.05437/) (2026)
- [EvBS: Event-guided Blur Synthesis for Domain-adaptive Motion Deblurring](https://mlsanity.com/paper/2608.08066/) (2026)

## Abstract (arXiv)

Zero-shot domain adaptation is a method for adapting a model to a target domain without utilizing target domain image data. To enable adaptation without target images, existing studies utilize CLIP's embedding space and text description to simulate target-like style features. Despite the previous achievements in zero-shot domain adaptation, we observe that these text-driven methods struggle to capture complex real-world variations and significantly increase adaptation time due to their alignment process. Instead of relying on text descriptions, we explore solutions leveraging image data, which provides diverse and more fine-grained style cues. In this work, we propose SIDA, a novel and efficient zero-shot domain adaptation method leveraging synthetic images. To generate synthetic images, we first create detailed, source-like images and apply image translation to reflect the style of the target domain. We then utilize the style features of these synthetic images as a proxy for the target domain. Based on these features, we introduce Domain Mix and Patch Style Transfer modules, which enable effective modeling of real-world variations. In particular, Domain Mix blends multiple styles to expand the intra-domain representations, and Patch Style Transfer assigns different styles to individual patches. We demonstrate the effectiveness of our method by showing state-of-the-art performance in diverse zero-shot adaptation scenarios, particularly in challenging domains. Moreover, our approach achieves high efficiency by significantly reducing the overall adaptation time.