# Style Evolving along Chain-of-Thought for Unknown-Domain Object Detection

arXiv: https://arxiv.org/abs/2503.09968 · HTML: https://mlsanity.com/paper/2503.09968/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 30 of its 38 references that are in the map.
- First posted on arXiv 13 Mar 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

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

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation](https://mlsanity.com/paper/1808.00897/) (2018)
- [Domain Adaptive Faster R-CNN for Object Detection in the Wild](https://mlsanity.com/paper/1803.03243/) (2018)
- [Open-Vocabulary Object Detection Using Captions](https://mlsanity.com/paper/2011.10678/) (2020)
- [Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net](https://mlsanity.com/paper/1807.09441/) (2018)
- [ConceptFusion: Open-set Multimodal 3D Mapping](https://mlsanity.com/paper/2302.07241/) (2023)
- [Learning to Learn Single Domain Generalization](https://mlsanity.com/paper/2003.13216/) (2020)
- [Frustratingly Simple Few-Shot Object Detection](https://mlsanity.com/paper/2003.06957/) (2020)
- [Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation](https://mlsanity.com/paper/1803.11365/) (2018)
- [RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening](https://mlsanity.com/paper/2103.15597/) (2021)
- [Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector](https://mlsanity.com/paper/1908.01998/) (2019)
- [CLIPstyler: Image Style Transfer with a Single Text Condition](https://mlsanity.com/paper/2112.00374/) (2021)
- [Learning to Diversify for Single Domain Generalization](https://mlsanity.com/paper/2108.11726/) (2021)
- [Unbiased Mean Teacher for Cross-domain Object Detection](https://mlsanity.com/paper/2003.00707/) (2020)
- [Single-Side Domain Generalization for Face Anti-Spoofing](https://mlsanity.com/paper/2004.14043/) (2020)
- [Causality-inspired Single-source Domain Generalization for Medical Image Segmentation](https://mlsanity.com/paper/2111.12525/) (2021)
- [Switchable Whitening for Deep Representation Learning](https://mlsanity.com/paper/1904.09739/) (2019)
- [Iterative Normalization: Beyond Standardization towards Efficient Whitening](https://mlsanity.com/paper/1904.03441/) (2019)
- [Towards Universal Object Detection by Domain Attention](https://mlsanity.com/paper/1904.04402/) (2019)
- [CLIP the Gap: A Single Domain Generalization Approach for Object Detection](https://mlsanity.com/paper/2301.05499/) (2023)
- [PODA: Prompt-driven Zero-shot Domain Adaptation](https://mlsanity.com/paper/2212.03241/) (2022)
- [PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization](https://mlsanity.com/paper/2307.15199/) (2023)
- [Progressive Semantic Segmentation](https://mlsanity.com/paper/2104.03778/) (2021)
- [Improving Single Domain-Generalized Object Detection: A Focus on Diversification and Alignment](https://mlsanity.com/paper/2405.14497/) (2024)
- [Unbiased Faster R-CNN for Single-source Domain Generalized Object Detection](https://mlsanity.com/paper/2405.15225/) (2024)
- [Prompt-Driven Dynamic Object-Centric Learning for Single Domain Generalization](https://mlsanity.com/paper/2402.18447/) (2024)
- [Prototype-guided Cross-task Knowledge Distillation for Large-scale Models](https://mlsanity.com/paper/2212.13180/) (2022)

## Built on by (most cited first, 6 of 6)

- [Wi-CBR: Salient-aware Adaptive WiFi Sensing for Cross-domain Behavior Recognition](https://mlsanity.com/paper/2506.11616/) (2025)
- [Towards Open Environments and Instructions: General Vision-Language Navigation via Fast-Slow Interactive Reasoning](https://mlsanity.com/paper/2601.09111/) (2026)
- [Geometric-Aware Hypergraph Reasoning for Novel Class Discovery in Point Cloud Segmentation](https://mlsanity.com/paper/2606.07280/) (2026)
- [Prototype-Anchored Generalized Manifold Regression for Unknown-Domain Object Detection](https://mlsanity.com/paper/2607.07192/) (2026)
- [Hierarchical Prompt Injector for Domain Generalization Segmentation](https://mlsanity.com/paper/2609.05864/) (2026)
- [Domain generalization and synthetic data in object detection: the enabler, the probe, and the gap](https://mlsanity.com/paper/2610.00030/) (2026)

## Abstract (arXiv)

Recently, a task of Single-Domain Generalized Object Detection (Single-DGOD) is proposed, aiming to generalize a detector to multiple unknown domains never seen before during training. Due to the unavailability of target-domain data, some methods leverage the multimodal capabilities of vision-language models, using textual prompts to estimate cross-domain information, enhancing the model's generalization capability. These methods typically use a single textual prompt, often referred to as the one-step prompt method. However, when dealing with complex styles such as the combination of rain and night, we observe that the performance of the one-step prompt method tends to be relatively weak. The reason may be that many scenes incorporate not just a single style but a combination of multiple styles. The one-step prompt method may not effectively synthesize combined information involving various styles. To address this limitation, we propose a new method, i.e., Style Evolving along Chain-of-Thought, which aims to progressively integrate and expand style information along the chain of thought, enabling the continual evolution of styles. Specifically, by progressively refining style descriptions and guiding the diverse evolution of styles, this approach enables more accurate simulation of various style characteristics and helps the model gradually learn and adapt to subtle differences between styles. Additionally, it exposes the model to a broader range of style features with different data distributions, thereby enhancing its generalization capability in unseen domains. The significant performance gains over five adverse-weather scenarios and the Real to Art benchmark demonstrate the superiorities of our method.