HamiPose：面向无监督域自适应姿态估计的哈密顿优化
HamiPose: Hamiltonian Optimization for Unsupervised Domain Adaptive Pose Estimation
把源域监督与目标域一致性之间的梯度冲突显式解耦：按关键点做几何分解、正交投影保留非冲突分量，再用通道门控按置信度校准平行分量，最后用辛普森积分器驱动的哈密顿优化器提供受控动量。做跨域关键点/姿态迁移时可直接复用这套梯度解耦+动量稳定更新的训练流程。
原文依据 we propose HamiPose, a Hamiltonian optimization framework that transports decoupled and confidence-calibrated gradients within a unified geometry to mitigate instability
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论面向姿态估计的无监督域自适应（UDA）有望实现从合成域到真实域的迁移，但在域偏移下常常出现不稳定的问题。已有工作将这种性能退化归因于源域监督与目标域一致性之间的梯度干扰。这一冲突在姿态估计中尤为突出：稀疏且异质的监督信号使梯度对微小的定位误差高度敏感，从而导致更新不稳定。为应对这些挑战，我们提出 HamiPose，一个哈密顿优化框架，它在统一的几何结构中传输解耦且经置信度校准的梯度，以缓解不稳定性。HamiPose 首先通过逐关键点的几何分解来精化梯度交互，对目标域梯度做正交投影以保留不冲突的分量；随后由通道门控对齐模块结合置信度与对齐程度来校准平行分量，从而得到解耦且经置信度校准的梯度。这些梯度由一个配备辛普森积分器的哈密顿优化器推进，提供受控的动量以稳定更新。大量实验表明，HamiPose 在无监督域自适应姿态估计上取得了最优性能，同时在域泛化设定下也保持了强劲的表现。
英文原文摘要 1310 字符
Unsupervised domain adaptation (UDA) for pose estimation promises transfer from synthetic to real domains but often suffers instability under domain shift. Prior work attributes this deterioration to gradient interference between source supervision and target consistency. This conflict is distinct in pose estimation, where sparse and heterogeneous supervision signals cause gradients to be highly sensitive to small localization errors and lead to unstable updates. To address these challenges, we propose HamiPose, a Hamiltonian optimization framework that transports decoupled and confidence-calibrated gradients within a unified geometry to mitigate instability. HamiPose first refines gradient interaction through keypointwise geometry decomposition, orthogonally projecting target gradients to preserve nonconflicting component. Channelwise gated alignment then calibrates the parallel component with confidence and alignment, producing decoupled, confidence-calibrated gradients. These gradients are advanced by a Hamiltonian optimizer with a symplectic integrator, providing controlled momentum that stabilizes updates. Extensive experiments demonstrate that HamiPose achieves state-of-the-art performance in UDA pose estimation while maintains strong performance under domain generalization settings.