差分隐私二维人体姿态估计
Differentially Private 2D Human Pose Estimation
将差分隐私训练引入2D人体姿态估计，通过梯度子空间投影和特征级隐私机制在形式化隐私约束下显著降低噪声方差，为视觉任务在敏感数据上的隐私保护部署提供了可复用的DP-SGD改进方案。
原文依据 We introduce the first unified framework for differentially private 2D Human Pose Estimation (2D-HPE)
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论人体姿态估计（HPE）是医疗保健、活动识别和人机交互等关键应用的基础。然而，处理敏感视觉数据带来的隐私影响在关键领域构成了显著的部署障碍。传统匿名化技术提供的保护较弱且不可量化，而差分隐私（DP）虽提供形式化保证，但往往导致严重的性能损失。我们提出了首个用于差分隐私二维人体姿态估计（2D-HPE）的统一框架，通过互补的噪声缓解机制在结构化视觉预测中实现强隐私-效用权衡。我们的特征投影DP集成了：（1）子空间投影，通过将梯度更新限制在全p维参数空间内的k维主成分子空间，将噪声方差降低k/p倍；（2）特征级隐私，选择性地对敏感特征进行私有化，同时保留公开视觉线索。这些机制共同在形式化隐私约束下产生乘性效用增益。我们进一步提出了一种特征投影混合方法，在单一后处理框架内结合两种机制。在MPII和HumanART数据集上，跨隐私预算（ε∈0.2, 0.4, 0.6, 0.8）、裁剪阈值（C∈0.01, 0.1, 1.0）和训练策略的大量实验表明，该方法相比原始DP-SGD取得了一致性改进。在ε=0.8时，我们的方法达到82.61% PCKh@0.5，恢复了73%的隐私导致的性能差距。在HumanART上的跨数据集评估证实了泛化性（51.6 AP）。我们的研究为敏感现实应用中的隐私保护姿态估计提供了首个严格基准和实用蓝图。源代码将在接收后公开。
英文原文摘要 1863 字符
Human pose estimation (HPE) underpins critical applications in healthcare, activity recognition, and human-computer interaction. However, the privacy implications of processing sensitive visual data present significant deployment barriers in critical domains. %Conventional anonymization techniques offer weak protection and are unquantifiable, while Differential Privacy (DP) provides formal guarantees but often results in steep performance costs.We introduce the first unified framework for differentially private 2D Human Pose Estimation (2D-HPE) that achieves strong privacy-utility trade-offs for structured visual prediction through complementary noise mitigation mechanisms. Our Feature-Projective DP integrates: (1) subspace projection that reduces noise variance by a factor k/p by restricting gradient updates to a k-principal subspace within the full p-dimensional parameter space, and (2) feature-level privacy, which selectively privatizes sensitive features while retaining public visual cues. Together these mechanisms yield a multiplicative utility gain under formal privacy constraints.%We further propose a feature-projective hybrid that combines both the mechanisms within a single post-processing framework.Extensive experiments on MPII and HumanART datasets across privacy budgets (\varepsilon \in \ 0.2, 0.4, 0.6, 0.8\ ), clipping thresholds (C \in \ 0.01, 0.1, 1.0\ ) and training strategies demonstrate consistent improvements over vanilla DP-SGD. At \varepsilon=0.8, our method achieves 82.61% PCKh@0.5, recovering 73% of the privacy induced performance gap. Cross-dataset evaluation on the HumanART confirms generalization (51.6 AP). Our study provides the first rigorous benchmark and a practical blueprint for privacy-preserving pose estimation in sensitive, real-world applications. Our source code will be made public on acceptance.