用扩散模型在测试时逆向转换图像，提升模型在极端环境下的鲁棒性。
Test-Time Modification: Inverse Domain Transformation for Robust Perception
- 测试时用扩散模型将目标域图像映射回源域分布
- 在夜间、模糊等挑战场景下性能显著提升
- 无需生成大量合成数据，适合实际部署
生成式基础模型具备广泛视觉知识，能生成多样图像，对提升域泛化能力极具潜力。传统方法依赖生成大量目标域样本进行数据增强，但过程缓慢、成本高且不完整。本文提出新思路：在测试阶段利用扩散模型将目标域图像逆向映射至下游模型训练的源域分布。该方法仅需源域描述信息，不修改原任务模型，避免大规模合成数据生成。我们在真实世界到真实世界的域泛化场景中验证了其有效性，面对未知目标分布的恶劣环境变化，均实现稳定提升。实验涵盖分割、检测与分类任务，覆盖多种生成模型与下游模型，包括集成变体以增强鲁棒性。结果表明，BDD100K-Night-Det mAP@50 从 10.2 提升至 31.8，ImageNet-R top-1 从 36.1 提升至 60.8，DarkZurich mIoU 从 28.6 提升至 46.3。
原文摘要 · Abstract (English)
Generative foundation models contain broad visual knowledge and can produce diverse image variations, making them particularly promising for advancing domain generalization tasks. They can be used for training data augmentation, but synthesizing comprehensive target-domain variations remains slow, expensive, and incomplete. We propose an alternative: using diffusion models at test time to map target images back to the source distribution where the downstream model was trained. This approach requires only a source domain description, preserves the task model, and eliminates large-scale synthetic data generation. We demonstrate consistent improvements across segmentation, detection, and classification tasks under challenging environmental shifts in real-to-real domain generalization scenarios with unknown target distributions. Our analysis spans multiple generative and downstream models, including an ensemble variant for enhanced robustness. The method improves BDD100K-Night-Det mAP@50 from 10.2 to 31.8, ImageNet-R top-1 from 36.1 to 60.8, and DarkZurich mIoU from 28.6 to 46.3.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。