arXiv 2412.024792025-03-27cs.CVcs.AIcs.CRcs.LG

OODFace：在常见损坏和外观变化下的人脸识别鲁棒性基准测试

OODFace: Benchmarking Robustness of Face Recognition under Common Corruptions and Appearance Variations

Institute of Artificial Intelligence, Beihang University（北京航空航天大学人工智能学院）；China Academy of Information and Communications Technology（中国信息通信研究院）

Caixin Kang, Yubo Chen, Shouwei Ruan, Shiji Zhao, Ruochen Zhang, Jiayi Wang, Shan Fu, Xingxing Wei

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出OODFace基准，从常见损坏和外观变化两方面系统评估人脸识别模型在分布外场景下的鲁棒性，发现现有模型脆弱，并提供统一工具包与改进方向。

摘要：

随着深度学习的兴起，人脸识别技术得到了广泛的研究和快速发展。尽管人脸识别被认为是一项成熟的技术，但我们发现现有的开源模型和商业算法在某些复杂的分布外（OOD）场景中缺乏鲁棒性，这引发了对这些系统可靠性的担忧。在本文中，我们引入了OODFace，从常见损坏和外观变化两个角度探索人脸识别模型面临的OOD挑战。我们针对人脸识别系统地设计了9大类共30种OOD场景。通过在公共数据集上模拟这些挑战，我们建立了三个鲁棒性基准：LFW-C/V、CFP-FP-C/V和YTF-C/V。随后，我们对19个人脸识别模型和3个商业API进行了广泛实验，并针对口罩进行了扩展的物理实验，以评估其鲁棒性。接下来，我们从防御策略和视觉语言模型（VLMs）两个角度探索潜在解决方案。基于实验结果，我们得出若干关键见解，强调人脸识别系统对OOD数据的脆弱性，并提出可能的解决方案。此外，我们提供了一个统一的工具包，包含所有损坏和变化类型，可轻松扩展到其他数据集。我们希望我们的基准和发现能为未来人脸识别模型鲁棒性的改进提供指导。

英文摘要：

With the rise of deep learning, facial recognition technology has seen extensive research and rapid development. Although facial recognition is considered a mature technology, we find that existing open-source models and commercial algorithms lack robustness in certain complex Out-of-Distribution (OOD) scenarios, raising concerns about the reliability of these systems. In this paper, we introduce OODFace, which explores the OOD challenges faced by facial recognition models from two perspectives: common corruptions and appearance variations. We systematically design 30 OOD scenarios across 9 major categories tailored for facial recognition. By simulating these challenges on public datasets, we establish three robustness benchmarks: LFW-C/V, CFP-FP-C/V, and YTF-C/V. We then conduct extensive experiments on 19 facial recognition models and 3 commercial APIs, along with extended physical experiments on face masks to assess their robustness. Next, we explore potential solutions from two perspectives: defense strategies and Vision-Language Models (VLMs). Based on the results, we draw several key insights, highlighting the vulnerability of facial recognition systems to OOD data and suggesting possible solutions. Additionally, we offer a unified toolkit that includes all corruption and variation types, easily extendable to other datasets. We hope that our benchmarks and findings can provide guidance for future improvements in facial recognition model robustness.

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。