Research map / Vision-language and multimodal / CLIP and zero-shot
PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization
Junhyeong Cho, Gilhyun Nam, Sungyeon Kim, Hunmin Yang, Suha Kwak
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add both style diversity and content consistency losses to style word vector learning (ablation) | PromptStyler · DG average (CLIP ResNet-50) | average accuracy: 72.8 -> 74.7 | Improved |
| add style diversity loss only (ablation) | PromptStyler · DG average (CLIP ResNet-50) | average accuracy: 72.8 -> 73.2 | Improved |
| add content consistency loss only (ablation) | PromptStyler · DG average (CLIP ResNet-50) | average accuracy: 72.8 -> 73.6 | Improved |
| use random unlearned style word vectors without either loss (ablation) | PromptStyler · DG average (CLIP ResNet-50) | average accuracy: 72.8 vs ZS-CLIP (PC) 72.3 | Improved |
| use ArcFace loss instead of softmax for classifier (ablation) | PromptStyler · DG average (CLIP ResNet-50) | average accuracy: 73.7 -> 74.7 | Improved |
| train classifier on synthesized style-content features without any image or source domain | CLIP ResNet-50 · DomainNet | accuracy: 45.6 -> 49.5 | Improved |
| drop text encoder at inference with trained linear classifier | PromptStyler · DomainNet | FPS: 0.3 -> 72.9 | Improved |
Later papers that compared with this method
1 later accepted paper reports PromptStyler as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- UMFC: Unsupervised Multi-Domain Feature Calibration for Vision-Language Models (NeurIPS 2024 · better on 1 of 1 shared result)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Domain-Agnostic Mutual Prompting for Unsupervised Domain Adaptation (CVPR 2024 · similarity 0.87)
- StyleStudio: Text-Driven Style Transfer with Selective Control of Style Elements (CVPR 2025 · similarity 0.86)
- Disentangled Prompt Representation for Domain Generalization (CVPR 2024 · similarity 0.86)
- Concept-Guided Prompt Learning for Generalization in Vision-Language Models (AAAI 2024 · similarity 0.85)
- Prompt-Based Distribution Alignment for Unsupervised Domain Adaptation (AAAI 2024 · similarity 0.85)
- Domain Generalization in CLIP via Learning with Diverse Text Prompts (CVPR 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
