# StyleAdv: Meta Style Adversarial Training for Cross-Domain Few-Shot Learning

arXiv: https://arxiv.org/abs/2302.09309 · HTML: https://mlsanity.com/paper/2302.09309/

## Key facts

- Cited by 53 papers in the map (data through 14 Oct 2026).
- Builds on 57 of its 76 references that are in the map.
- First posted on arXiv 18 Feb 2023.

## Builds on (most cited first, 30 of 57)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification](https://mlsanity.com/paper/1709.00029/) (2017)
- [DeepFool: a simple and accurate method to fool deep neural networks](https://mlsanity.com/paper/1511.04599/) (2015)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases](https://mlsanity.com/paper/1705.02315/) (2017)
- [Practical Black-Box Attacks against Machine Learning](https://mlsanity.com/paper/1602.02697/) (2016)
- [The Limitations of Deep Learning in Adversarial Settings](https://mlsanity.com/paper/1511.07528/) (2015)
- [Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)](https://mlsanity.com/paper/1902.03368/) (2019)
- [One pixel attack for fooling deep neural networks](https://mlsanity.com/paper/1710.08864/) (2017)
- [Domain Generalization with MixStyle](https://mlsanity.com/paper/2104.02008/) (2021)
- [Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling](https://mlsanity.com/paper/2111.03930/) (2021)
- [Few-Shot Learning with Graph Neural Networks](https://mlsanity.com/paper/1711.04043/) (2017)
- [Meta-Transfer Learning for Few-Shot Learning](https://mlsanity.com/paper/1812.02391/) (2018)
- [Adversarial Examples Improve Image Recognition](https://mlsanity.com/paper/1911.09665/) (2019)
- [Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2003.03773/) (2020)
- [Using Deep Learning for Image-Based Plant Disease Detection](https://mlsanity.com/paper/1604.03169/) (2016)
- [Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation](https://mlsanity.com/paper/2001.08735/) (2020)
- [Learning to Diversify for Single Domain Generalization](https://mlsanity.com/paper/2108.11726/) (2021)
- [Adversarial Camouflage: Hiding Physical-World Attacks with Natural Styles](https://mlsanity.com/paper/2003.08757/) (2020)

## Built on by (most cited first, 30 of 53)

- [DePT: Decoupled Prompt Tuning](https://mlsanity.com/paper/2309.07439/) (2023)
- [Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector](https://mlsanity.com/paper/2402.03094/) (2024)
- [Enhance Then Search: An Augmentation-Search Strategy with Foundation Models for Cross-Domain Few-Shot Object Detection](https://mlsanity.com/paper/2504.04517/) (2025)
- [Adapt Before Comparison: A New Perspective on Cross-Domain Few-Shot Segmentation](https://mlsanity.com/paper/2402.17614/) (2024)
- [EgoCross: Benchmarking Multimodal Large Language Models for Cross-Domain Egocentric Video Question Answering](https://mlsanity.com/paper/2508.10729/) (2025)
- [EgoNight: Towards Egocentric Vision Understanding at Night with a Challenging Benchmark](https://mlsanity.com/paper/2510.06218/) (2025)
- [Reliable Few-shot Learning under Dual Noises](https://mlsanity.com/paper/2506.16330/) (2025)
- [Simple Semantic-Aided Few-Shot Learning](https://mlsanity.com/paper/2311.18649/) (2023)
- [Domain-RAG: Retrieval-Guided Compositional Image Generation for Cross-Domain Few-Shot Object Detection](https://mlsanity.com/paper/2506.05872/) (2025)
- [Learning to Adapt Frozen CLIP for Few-Shot Test-Time Domain Adaptation](https://mlsanity.com/paper/2506.17307/) (2025)
- [DETA: Denoised Task Adaptation for Few-Shot Learning](https://mlsanity.com/paper/2303.06315/) (2023)
- [Enhancing Information Maximization with Distance-Aware Contrastive Learning for Source-Free Cross-Domain Few-Shot Learning](https://mlsanity.com/paper/2403.01966/) (2024)
- [EarthSynth: Generating Informative Earth Observation with Diffusion Models](https://mlsanity.com/paper/2505.12108/) (2025)
- [On the Importance of Spatial Relations for Few-shot Action Recognition](https://mlsanity.com/paper/2308.07119/) (2023)
- [Meta-Exploiting Frequency Prior for Cross-Domain Few-Shot Learning](https://mlsanity.com/paper/2411.01432/) (2024)
- [Skip Tuning: Pre-trained Vision-Language Models are Effective and Efficient Adapters Themselves](https://mlsanity.com/paper/2412.11509/) (2024)
- [Connecting Giants: Synergistic Knowledge Transfer of Large Multimodal Models for Few-Shot Learning](https://mlsanity.com/paper/2510.11115/) (2025)
- [A Closer Look at Conditional Prompt Tuning for Vision-Language Models](https://mlsanity.com/paper/2506.23856/) (2025)
- [Cross-Domain Few-Shot Learning via Adaptive Transformer Networks](https://mlsanity.com/paper/2401.13987/) (2024)
- [VT-FSL: Bridging Vision and Text with LLMs for Few-Shot Learning](https://mlsanity.com/paper/2509.25033/) (2025)
- [StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization](https://mlsanity.com/paper/2406.00275/) (2024)
- [Towards Few-Shot Learning in the Open World: A Review and Beyond](https://mlsanity.com/paper/2408.09722/) (2024)
- [Step-wise Distribution Alignment Guided Style Prompt Tuning for Source-free Cross-domain Few-shot Learning](https://mlsanity.com/paper/2411.10070/) (2024)
- [Style-Pro: Style-Guided Prompt Learning for Generalizable Vision-Language Models](https://mlsanity.com/paper/2411.16018/) (2024)
- [Reclaiming Lost Text Layers for Source-Free Cross-Domain Few-Shot Learning](https://mlsanity.com/paper/2603.05235/) (2026)
- [Enhancing Few-Shot Image Classification through Learnable Multi-Scale Embedding and Attention Mechanisms](https://mlsanity.com/paper/2409.07989/) (2024)
- [Mind the Discriminability Trap in Source-Free Cross-domain Few-shot Learning](https://mlsanity.com/paper/2603.13341/) (2026)
- [Interpretable Cross-Domain Few-Shot Learning with Rectified Target-Domain Local Alignment](https://mlsanity.com/paper/2603.17655/) (2026)
- [SETA: Semantic-Aware Token Augmentation for Domain Generalization](https://mlsanity.com/paper/2403.11792/) (2024)
- [Few-Shot Vision-Language Action-Incremental Policy Learning](https://mlsanity.com/paper/2504.15517/) (2025)

## Abstract (arXiv)

Cross-Domain Few-Shot Learning (CD-FSL) is a recently emerging task that tackles few-shot learning across different domains. It aims at transferring prior knowledge learned on the source dataset to novel target datasets. The CD-FSL task is especially challenged by the huge domain gap between different datasets. Critically, such a domain gap actually comes from the changes of visual styles, and wave-SAN empirically shows that spanning the style distribution of the source data helps alleviate this issue. However, wave-SAN simply swaps styles of two images. Such a vanilla operation makes the generated styles ``real'' and ``easy'', which still fall into the original set of the source styles. Thus, inspired by vanilla adversarial learning, a novel model-agnostic meta Style Adversarial training (StyleAdv) method together with a novel style adversarial attack method is proposed for CD-FSL. Particularly, our style attack method synthesizes both ``virtual'' and ``hard'' adversarial styles for model training. This is achieved by perturbing the original style with the signed style gradients. By continually attacking styles and forcing the model to recognize these challenging adversarial styles, our model is gradually robust to the visual styles, thus boosting the generalization ability for novel target datasets. Besides the typical CNN-based backbone, we also employ our StyleAdv method on large-scale pretrained vision transformer. Extensive experiments conducted on eight various target datasets show the effectiveness of our method. Whether built upon ResNet or ViT, we achieve the new state of the art for CD-FSL. Code is available at https://github.com/lovelyqian/StyleAdv-CDFSL.