发表机构
TNO - Defence, Security and Safety; FOI - Swedish Defence Research Agency（荷兰应用科学研究组织（TNO）国防安全与安保部门; 瑞典国防研究局）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文以目标检测为中心综述域泛化，从使能器、探针和合成到真实差距三视角审视合成数据作用，指出需表示感知方法处理域偏移下的定位与分类。
AI 中文摘要
目标检测模型在部署时常常因分布偏移而出现性能下降，这些偏移可能由天气类型、运行环境或物体外观的变化引起。域泛化（DG）旨在开发在此类偏移下保持稳健并能良好泛化到未见域模型。专门针对目标检测模型的域泛化研究较为稀缺，尽管这些模型在定位和多尺度表示方面面临额外挑战。合成数据是支持域泛化的有前景工具，它能大规模生成多样化的新样本。在本文中，我们呈现了一个以目标检测为中心的域泛化综述，并从三个互补视角审视合成数据的作用。首先，合成数据通过多样化和对齐策略作为域泛化的使能器，旨在提高对分布偏移的稳健性。其次，它作为探针，支持受控实验以识别和理解失败模式。第三，我们讨论了合成到真实的差距，这是一种特别具有挑战性的域偏移形式，当在合成图像上训练的模型部署于真实世界数据时会出现。通过综述这些视角，我们识别了当前目标检测域泛化方法的局限性，并认为未来研究需要表示感知的方法，这些方法应明确处理域偏移下的定位和分类问题。
英文摘要
Object detection models often experience performance degradation when deployed under distribution shifts, caused by for example changes in weather type, operational environment, or object appearance. Domain Generalization (DG) aims to develop models that remain robust under such shifts and generalize well to unseen domains. DG research specifically focused on object detection models is scarce, although these models face additional challenges around localization and multi-scale representations. Synthetic data is a promising tool to support in DG, by enabling large-scale generation of diverse new samples. In this paper, we present an object detection-centric review of DG and examine the role of synthetic data from three complementary perspectives. First, synthetic data acts as an enabler of DG through diversification and alignment strategies that aim to improve robustness to distribution shifts. Second, it serves as a probe that enables controlled experimentation to identify and understand failure modes. Third, we discuss the synthetic-to-real gap, a particularly challenging form of domain shift that arises when models trained on synthetic imagery are deployed on real-world data. Through reviewing these perspectives, we identify limitations of current DG approaches for object detection and argue that future research requires representation-aware methods that explicitly address both localization and classification under domain shift.
CommentsSubmitted to SPIE Sensors + Imaging 2026
