# Adversarial Style Mining for One-Shot Unsupervised Domain Adaptation

arXiv: https://arxiv.org/abs/2004.06042 · HTML: https://mlsanity.com/paper/2004.06042/

## Key facts

- Cited by 64 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Apr 2020.

## Built on by (most cited first, 30 of 64)

- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Unsupervised Domain Adaptation of Object Detectors: A Survey](https://mlsanity.com/paper/2105.13502/) (2021)
- [Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2108.11249/) (2021)
- [MT3: Meta Test-Time Training for Self-Supervised Test-Time Adaption](https://mlsanity.com/paper/2103.16201/) (2021)
- [PODA: Prompt-driven Zero-shot Domain Adaptation](https://mlsanity.com/paper/2212.03241/) (2022)
- [Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector](https://mlsanity.com/paper/2402.03094/) (2024)
- [One-shot Unsupervised Domain Adaptation with Personalized Diffusion Models](https://mlsanity.com/paper/2303.18080/) (2023)
- [Feature-based Style Randomization for Domain Generalization](https://mlsanity.com/paper/2106.03171/) (2021)
- [Data-Free Knowledge Transfer: A Survey](https://mlsanity.com/paper/2112.15278/) (2021)
- [Unified Language-driven Zero-shot Domain Adaptation](https://mlsanity.com/paper/2404.07155/) (2024)
- [Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Driving](https://mlsanity.com/paper/2304.11928/) (2023)
- [Learning to Generalize across Domains on Single Test Samples](https://mlsanity.com/paper/2202.08045/) (2022)
- [Learning Spectral-Decomposed Tokens for Domain Generalized Semantic Segmentation](https://mlsanity.com/paper/2407.18568/) (2024)
- [Any-to-Any Style Transfer: Making Picasso and Da Vinci Collaborate](https://mlsanity.com/paper/2304.09728/) (2023)
- [Free-form tumor synthesis in computed tomography images via richer generative adversarial network](https://mlsanity.com/paper/2104.09701/) (2021)
- [Active Learning for Point Cloud Semantic Segmentation via Spatial-Structural Diversity Reasoning](https://mlsanity.com/paper/2202.12588/) (2022)
- [Adversarial Style Augmentation for Domain Generalization](https://mlsanity.com/paper/2301.12643/) (2023)
- [Pixel-by-Pixel Cross-Domain Alignment for Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2110.11650/) (2021)
- [Style Mixing and Patchwise Prototypical Matching for One-Shot Unsupervised Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2112.04665/) (2021)
- [Improving Weakly-supervised Object Localization via Causal Intervention](https://mlsanity.com/paper/2104.10351/) (2021)
- [Adaptive Boosting for Domain Adaptation: Towards Robust Predictions in Scene Segmentation](https://mlsanity.com/paper/2103.15685/) (2021)
- [Learning Instance-Specific Adaptation for Cross-Domain Segmentation](https://mlsanity.com/paper/2203.16530/) (2022)
- [Introducing Intermediate Domains for Effective Self-Training during Test-Time](https://mlsanity.com/paper/2208.07736/) (2022)
- [Clustering Propagation for Universal Medical Image Segmentation](https://mlsanity.com/paper/2403.16646/) (2024)
- [Domain-robust VQA with diverse datasets and methods but no target labels](https://mlsanity.com/paper/2103.15974/) (2021)
- [Distance-based Hyperspherical Classification for Multi-source Open-Set Domain Adaptation](https://mlsanity.com/paper/2107.02067/) (2021)
- [Bidirectional Self-Training with Multiple Anisotropic Prototypes for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2204.07730/) (2022)
- [Inter-Domain Mixup for Semi-Supervised Domain Adaptation](https://mlsanity.com/paper/2401.11453/) (2024)
- [Adversarial Semantic Hallucination for Domain Generalized Semantic Segmentation](https://mlsanity.com/paper/2106.04144/) (2021)
- [TTAPS: Test-Time Adaption by Aligning Prototypes using Self-Supervision](https://mlsanity.com/paper/2205.08731/) (2022)

## Abstract (arXiv)

We aim at the problem named One-Shot Unsupervised Domain Adaptation. Unlike traditional Unsupervised Domain Adaptation, it assumes that only one unlabeled target sample can be available when learning to adapt. This setting is realistic but more challenging, in which conventional adaptation approaches are prone to failure due to the scarce of unlabeled target data. To this end, we propose a novel Adversarial Style Mining approach, which combines the style transfer module and task-specific module into an adversarial manner. Specifically, the style transfer module iteratively searches for harder stylized images around the one-shot target sample according to the current learning state, leading the task model to explore the potential styles that are difficult to solve in the almost unseen target domain, thus boosting the adaptation performance in a data-scarce scenario. The adversarial learning framework makes the style transfer module and task-specific module benefit each other during the competition. Extensive experiments on both cross-domain classification and segmentation benchmarks verify that ASM achieves state-of-the-art adaptation performance under the challenging one-shot setting.