arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2503.02101cs.CV
收藏

广义扩散检测器:从扩散模型中挖掘鲁棒特征用于域泛化检测

Generalized Diffusion Detector: Mining Robust Features from Diffusion Models for Domain-Generalized Detection

Institute of Artifcial Intelligence, Xiamen University(厦门大学人工智能学院);School of Aerospace Engineering, Xiamen University(厦门大学航空航天工程学院)

Boyong He, Yuxiang Ji, Qianwen Ye, Zhuoyue Tan, Liaoni Wu

AI总结:

本文提出广义扩散检测器,通过提取扩散模型多步中间特征获得域不变特征,并设计高效知识迁移框架,在六个DG基准上显著提升域泛化检测性能。

摘要:

面向目标检测的域泛化(DG)旨在提升检测器在未见场景中的性能。由于现实应用中存在复杂的分布变化,该任务仍然具有挑战性。近年来,扩散模型在多样化场景生成方面展现出卓越能力,这启发我们探索其在改进DG任务中的潜力。与生成图像不同,我们的方法在扩散过程中提取多步中间特征,以获得用于泛化检测的域不变特征。此外,我们提出了一种高效的知识迁移框架,使检测器能够通过特征级和目标级对齐继承扩散模型的泛化能力,同时不增加推理时间。我们在六个具有挑战性的DG基准上进行了大量实验。结果表明,与现有DG方法相比,我们的方法在不同域和损坏类型上实现了14.0% mAP的显著提升。值得注意的是,我们的方法甚至在不访问任何目标域数据的情况下超越了大多数域自适应方法。此外,与基线相比,扩散引导的检测器平均实现了15.9% mAP的一致提升。我们的工作旨在为域泛化检测提供一种有效方法,并为现实场景中的鲁棒视觉识别提供潜在见解。代码可在https://github.com/heboyong/Generalized-Diffusion-Detector获取。

英文摘要:

Domain generalization (DG) for object detection aims to enhance detectors' performance in unseen scenarios. This task remains challenging due to complex variations in real-world applications. Recently, diffusion models have demonstrated remarkable capabilities in diverse scene generation, which inspires us to explore their potential for improving DG tasks. Instead of generating images, our method extracts multi-step intermediate features during the diffusion process to obtain domain-invariant features for generalized detection. Furthermore, we propose an efficient knowledge transfer framework that enables detectors to inherit the generalization capabilities of diffusion models through feature and object-level alignment, without increasing inference time. We conduct extensive experiments on six challenging DG benchmarks. The results demonstrate that our method achieves substantial improvements of 14.0% mAP over existing DG approaches across different domains and corruption types. Notably, our method even outperforms most domain adaptation methods without accessing any target domain data. Moreover, the diffusion-guided detectors show consistent improvements of 15.9% mAP on average compared to the baseline. Our work aims to present an effective approach for domain-generalized detection and provide potential insights for robust visual recognition in real-world scenarios. The code is available at https://github.com/heboyong/Generalized-Diffusion-Detector.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑