# StyLIP: Multi-Scale Style-Conditioned Prompt Learning for CLIP-based Domain Generalization

arXiv: https://arxiv.org/abs/2302.09251 · HTML: https://mlsanity.com/paper/2302.09251/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- Builds on 53 of its 83 references that are in the map.
- First posted on arXiv 18 Feb 2023.

## Builds on (most cited first, 30 of 53)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification](https://mlsanity.com/paper/1709.00029/) (2017)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [In Search of Lost Domain Generalization](https://mlsanity.com/paper/2007.01434/) (2020)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [Deeper, Broader and Artier Domain Generalization](https://mlsanity.com/paper/1710.03077/) (2017)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Learning to Generalize: Meta-Learning for Domain Generalization](https://mlsanity.com/paper/1710.03463/) (2017)
- [MaPLe: Multi-modal Prompt Learning](https://mlsanity.com/paper/2210.03117/) (2022)
- [Data-Efficient Image Recognition with Contrastive Predictive Coding](https://mlsanity.com/paper/1905.09272/) (2019)
- [A Survey on Visual Transformer](https://mlsanity.com/paper/2012.12556/) (2020)
- [Domain Generalization with MixStyle](https://mlsanity.com/paper/2104.02008/) (2021)
- [Domain Generalization by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1903.06864/) (2019)
- [SWAD: Domain Generalization by Seeking Flat Minima](https://mlsanity.com/paper/2102.08604/) (2021)
- [Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models](https://mlsanity.com/paper/2209.07511/) (2022)
- [Prompt-aligned Gradient for Prompt Tuning](https://mlsanity.com/paper/2205.14865/) (2022)
- [Learning to Learn Single Domain Generalization](https://mlsanity.com/paper/2003.13216/) (2020)
- [Learning to Generate Novel Domains for Domain Generalization](https://mlsanity.com/paper/2007.03304/) (2020)
- [Generalizing Across Domains via Cross-Gradient Training](https://mlsanity.com/paper/1804.10745/) (2018)

## Built on by (most cited first, 30 of 36)

- [AD-CLIP: Adapting Domains in Prompt Space Using CLIP](https://mlsanity.com/paper/2308.05659/) (2023)
- [DiffCLIP: Leveraging Stable Diffusion for Language Grounded 3D Classification](https://mlsanity.com/paper/2305.15957/) (2023)
- [Prompt-based Adaptation in Large-scale Vision Models: A Survey](https://mlsanity.com/paper/2510.13219/) (2025)
- [Unknown Prompt, the only Lacuna: Unveiling CLIP's Potential for Open Domain Generalization](https://mlsanity.com/paper/2404.00710/) (2024)
- [CLIP-Powered Domain Generalization and Domain Adaptation: A Comprehensive Survey](https://mlsanity.com/paper/2504.14280/) (2025)
- [LanDA: Language-Guided Multi-Source Domain Adaptation](https://mlsanity.com/paper/2401.14148/) (2024)
- [Diverse Target and Contribution Scheduling for Domain Generalization](https://mlsanity.com/paper/2309.16460/) (2023)
- [Prompt as Free Lunch: Enhancing Diversity in Source-Free Cross-domain Few-shot Learning through Semantic-Guided Prompting](https://mlsanity.com/paper/2412.00767/) (2024)
- [Exploring the Transfer Learning Capabilities of CLIP in Domain Generalization for Diabetic Retinopathy](https://mlsanity.com/paper/2308.14212/) (2023)
- [Generalizing vision-language models to novel domains: A comprehensive survey](https://mlsanity.com/paper/2506.18504/) (2025)
- [CoPT: Unsupervised Domain Adaptive Segmentation using Domain-Agnostic Text Embeddings](https://mlsanity.com/paper/2507.07125/) (2025)
- [Reasoning-Driven Multimodal LLM for Domain Generalization](https://mlsanity.com/paper/2602.23777/) (2026)
- [C-SAW: Self-Supervised Prompt Learning for Image Generalization in Remote Sensing](https://mlsanity.com/paper/2311.15812/) (2023)
- [OSLoPrompt: Bridging Low-Supervision Challenges and Open-Set Domain Generalization in CLIP](https://mlsanity.com/paper/2503.16106/) (2025)
- [COSMo: CLIP Talks on Open-Set Multi-Target Domain Adaptation](https://mlsanity.com/paper/2409.00397/) (2024)
- [Style-Pro: Style-Guided Prompt Learning for Generalizable Vision-Language Models](https://mlsanity.com/paper/2411.16018/) (2024)
- [GOPro: Generate and Optimize Prompts in CLIP using Self-Supervised Learning](https://mlsanity.com/paper/2308.11605/) (2023)
- [BatStyler: Advancing Multi-category Style Generation for Source-free Domain Generalization](https://mlsanity.com/paper/2501.01109/) (2025)
- [FedMVP: Federated Multimodal Visual Prompt Tuning for Vision-Language Models](https://mlsanity.com/paper/2504.20860/) (2025)
- [UPRE: Zero-Shot Domain Adaptation for Object Detection via Unified Prompt and Representation Enhancement](https://mlsanity.com/paper/2507.00721/) (2025)
- [Elevating All Zero-Shot Sketch-Based Image Retrieval Through Multimodal Prompt Learning](https://mlsanity.com/paper/2407.04207/) (2024)
- [FrogDogNet: Fourier frequency Retained visual prompt Output Guidance for Domain Generalization of CLIP in Remote Sensing](https://mlsanity.com/paper/2504.16433/) (2025)
- [Simulate, Refocus and Ensemble: An Attention-Refocusing Scheme for Domain Generalization](https://mlsanity.com/paper/2507.12851/) (2025)
- [Enhancing Vision-Language Models Generalization via Diversity-Driven Novel Feature Synthesis](https://mlsanity.com/paper/2405.02586/) (2024)
- [GraphVL: Graph-Enhanced Semantic Modeling via Vision-Language Models for Generalized Class Discovery](https://mlsanity.com/paper/2411.02074/) (2024)
- [Attention Head Purification: A New Perspective to Harness CLIP for Domain Generalization](https://mlsanity.com/paper/2412.07226/) (2024)
- [UCDR-Adapter: Exploring Adaptation of Pre-Trained Vision-Language Models for Universal Cross-Domain Retrieval](https://mlsanity.com/paper/2412.10680/) (2024)
- [Zero-Shot Anomaly Detection with Dual-Branch Prompt Selection](https://mlsanity.com/paper/2508.00777/) (2025)
- [Text-conditioned State Space Model For Domain-generalized Change Detection Visual Question Answering](https://mlsanity.com/paper/2508.08974/) (2025)
- [Latent Domain Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2511.00067/) (2025)

## Abstract (arXiv)

Large-scale foundation models, such as CLIP, have demonstrated impressive zero-shot generalization performance on downstream tasks, leveraging well-designed language prompts. However, these prompt learning techniques often struggle with domain shift, limiting their generalization capabilities. In our study, we tackle this issue by proposing StyLIP, a novel approach for Domain Generalization (DG) that enhances CLIP's classification performance across domains. Our method focuses on a domain-agnostic prompt learning strategy, aiming to disentangle the visual style and content information embedded in CLIP's pre-trained vision encoder, enabling effortless adaptation to novel domains during inference. To achieve this, we introduce a set of style projectors that directly learn the domain-specific prompt tokens from the extracted multi-scale style features. These generated prompt embeddings are subsequently combined with the multi-scale visual content features learned by a content projector. The projectors are trained in a contrastive manner, utilizing CLIP's fixed vision and text backbones. Through extensive experiments conducted in five different DG settings on multiple benchmark datasets, we consistently demonstrate that StyLIP outperforms the current state-of-the-art (SOTA) methods.