# Prototype-Anchored Generalized Manifold Regression for Unknown-Domain Object Detection

arXiv: https://arxiv.org/abs/2607.07192 · HTML: https://mlsanity.com/paper/2607.07192/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 60 references that are in the map.
- First posted on arXiv 8 Jul 2026.

## Builds on (most cited first, 30 of 31)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [Diffusion Models in Vision: A Survey](https://mlsanity.com/paper/2209.04747/) (2022)
- [OpenAI GPT-5 System Card](https://mlsanity.com/paper/2601.03267/) (2025)
- [Playing for Data: Ground Truth from Computer Games](https://mlsanity.com/paper/1608.02192/) (2016)
- [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model](https://mlsanity.com/paper/2208.15001/) (2022)
- [YOLOv10: Real-Time End-to-End Object Detection](https://mlsanity.com/paper/2405.14458/) (2024)
- [DiffusionDet: Diffusion Model for Object Detection](https://mlsanity.com/paper/2211.09788/) (2022)
- [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)
- [CLIPstyler: Image Style Transfer with a Single Text Condition](https://mlsanity.com/paper/2112.00374/) (2021)
- [Switchable Whitening for Deep Representation Learning](https://mlsanity.com/paper/1904.09739/) (2019)
- [A Comprehensive Survey on Source-free Domain Adaptation](https://mlsanity.com/paper/2302.11803/) (2023)
- [PODA: Prompt-driven Zero-shot Domain Adaptation](https://mlsanity.com/paper/2212.03241/) (2022)
- [Source-Free Domain Adaptation with Frozen Multimodal Foundation Model](https://mlsanity.com/paper/2311.16510/) (2023)
- [Vector-Decomposed Disentanglement for Domain-Invariant Object Detection](https://mlsanity.com/paper/2108.06685/) (2021)
- [Behind Every Domain There is a Shift: Adapting Distortion-aware Vision Transformers for Panoramic Semantic Segmentation](https://mlsanity.com/paper/2207.11860/) (2022)
- [Universal-Prototype Enhancing for Few-Shot Object Detection](https://mlsanity.com/paper/2103.01077/) (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)
- [SRCD: Semantic Reasoning with Compound Domains for Single-Domain Generalized Object Detection](https://mlsanity.com/paper/2307.01750/) (2023)
- [Prompt-Driven Dynamic Object-Centric Learning for Single Domain Generalization](https://mlsanity.com/paper/2402.18447/) (2024)
- [G-NAS: Generalizable Neural Architecture Search for Single Domain Generalization Object Detection](https://mlsanity.com/paper/2402.04672/) (2024)
- [Robust Domain Adaptive Object Detection with Unified Multi-Granularity Alignment](https://mlsanity.com/paper/2301.00371/) (2023)
- [Style Evolving along Chain-of-Thought for Unknown-Domain Object Detection](https://mlsanity.com/paper/2503.09968/) (2025)

## Abstract (arXiv)

In this paper, we study Single-Domain Generalized Object Detection (Single-DGOD), which aims to transfer a detector trained on a single source domain to multiple unseen domains. Existing methods mainly rely on simulation-driven strategies, such as data augmentation or textual prompts, to enlarge the training distribution. However, finite simulations can hardly cover the dynamic variations of real-world scenarios, often causing overfitting to synthetic styles and limited robustness to complex structural degradations. Inspired by the manifold hypothesis, we argue that semantic features, despite diverse visual changes, should lie on a compact and stable low-dimensional manifold. Therefore, robust generalization requires rectifying deviant samples back to this semantic manifold, rather than exhaustively simulating external perturbations. To this end, we propose Manifold Regression with Visual-Text Dual Chain-of-Thought (MR-DCoT), which formulates unknown-domain generalization as a manifold regression problem. MR-DCoT first uses a Visual-Text Dual Chain-of-Thought module to combine VLM-guided semantic evolution with diffusion-based structural perturbation, generating structured off-manifold hard examples. It then introduces Class-Specific Prototype Anchoring to learn a rectification operator that projects deviant features toward the source semantic manifold. By integrating outlier generation and semantic correction into a closed loop, MR-DCoT effectively narrows the distribution gap and improves robustness under unseen shifts. Extensive experiments on three complementary benchmarks, including adverse-weather detection, real-to-art generalization, and zero-shot semantic segmentation, demonstrate the effectiveness and versatility of our method.