# Adversarial Learning for Zero-shot Domain Adaptation

arXiv: https://arxiv.org/abs/2009.05214 · HTML: https://mlsanity.com/paper/2009.05214/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Sep 2020.

## Built on by (most cited first, 7 of 7)

- [Using Language to Extend to Unseen Domains](https://mlsanity.com/paper/2210.09520/) (2022)
- [Improving Automated Program Repair with Domain Adaptation](https://mlsanity.com/paper/2212.11414/) (2022)
- [ZoDi: Zero-Shot Domain Adaptation with Diffusion-Based Image Transfer](https://mlsanity.com/paper/2403.13652/) (2024)
- [UPRE: Zero-Shot Domain Adaptation for Object Detection via Unified Prompt and Representation Enhancement](https://mlsanity.com/paper/2507.00721/) (2025)
- [Domain Adaptation for Inertial Measurement Unit-based Human Activity Recognition: A Survey](https://mlsanity.com/paper/2304.06489/) (2023)
- [Few-Shot Object Detection in Unseen Domains](https://mlsanity.com/paper/2204.05072/) (2022)
- [Zero-shot domain adaptation based on dual-level mix and contrast](https://mlsanity.com/paper/2406.18996/) (2024)

## Abstract (arXiv)

Zero-shot domain adaptation (ZSDA) is a category of domain adaptation problems where neither data sample nor label is available for parameter learning in the target domain. With the hypothesis that the shift between a given pair of domains is shared across tasks, we propose a new method for ZSDA by transferring domain shift from an irrelevant task (IrT) to the task of interest (ToI). Specifically, we first identify an IrT, where dual-domain samples are available, and capture the domain shift with a coupled generative adversarial networks (CoGAN) in this task. Then, we train a CoGAN for the ToI and restrict it to carry the same domain shift as the CoGAN for IrT does. In addition, we introduce a pair of co-training classifiers to regularize the training procedure of CoGAN in the ToI. The proposed method not only derives machine learning models for the non-available target-domain data, but also synthesizes the data themselves. We evaluate the proposed method on benchmark datasets and achieve the state-of-the-art performances.