具有受控隐私保护与特征补偿的面部表情识别
Facial Expression Recognition with Controlled Privacy Preservation and Feature Compensation
AI总结：
针对FER中的身份隐私泄露问题，提出按频率分量分别增强隐私的双流框架，配合受控隐私增强、特征补偿及可量化隐私—效用权衡，在CREMA-D上以2.01%泄漏率取得78.84%准确率。
摘要：
面部表情识别（FER）系统因敏感身份信息可能暴露而引发显著的隐私担忧。本文研究了在保留FER能力的同时去除身份信息的问题。基于低频成分主要包含身份信息、高频成分捕捉表情这一观察，我们提出了一种新颖的双流框架，分别对每个成分施加隐私增强。我们引入了一种受控隐私增强机制以优化性能，并设计了特征补偿器，在不损害隐私的前提下增强与任务相关的特征。此外，我们提出了一种新颖的隐私—效用权衡方法，为闭集FER任务中的隐私保护效果提供可量化的度量。在基准CREMA-D数据集上的大量实验表明，我们的框架实现了78.84%的识别准确率，而隐私（面部身份）泄漏率仅为2.01%，凸显了其在安全可靠的基于视频的FER应用中的潜力。
英文摘要：
Facial expression recognition (FER) systems raise significant privacy concerns due to the potential exposure of sensitive identity information. This paper presents a study on removing identity information while preserving FER capabilities. Drawing on the observation that low-frequency components predominantly contain identity information and high-frequency components capture expression, we propose a novel two-stream framework that applies privacy enhancement to each component separately. We introduce a controlled privacy enhancement mechanism to optimize performance and a feature compensator to enhance task-relevant features without compromising privacy. Furthermore, we propose a novel privacy-utility trade-off, providing a quantifiable measure of privacy preservation efficacy in closed-set FER tasks. Extensive experiments on the benchmark CREMA-D dataset demonstrate that our framework achieves 78.84% recognition accuracy with a privacy (facial identity) leakage ratio of only 2.01%, highlighting its potential for secure and reliable video-based FER applications.
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。
