解剖域偏移：面向三维人体姿态预测的测试时异构自适应
Anatomical Domain Shifts: Test-time Heterogeneous Adaptation for 3D Human Pose Prediction
把测试时自适应的参数更新按人体解剖部位（躯干、四肢等）分组，用 Fisher 信息矩阵划分参数子集、用 IN 统计量与 EMD 度量各部位的域偏移程度，从而只对发生偏移的肢体做微调或回滚——这套「按语义部位分组 + 分组级域差异度量」的思路可直接迁移到人体姿态/动作预测、人体网格恢复等任务中应对局部域偏移。
原文依据 TT-HA partitions parameters into five anatomical subsets using fisher information matrix-based parameters uncertainty analysis.
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预测（HPP）的研究前沿正朝着持续测试时自适应（TTA）推进，模型必须自我适应动态变化的测试分布。迄今为止，稳态持续 TTA 仍是唯一可行的方案，它隔离模型参数并只更新对域敏感的参量。尽管该方法缓解了全身层面的域差异，却忽略了人体解剖层面的异质性（域偏移往往只局限于特定区域）。这种与解剖结构无关的做法迫使运动学上彼此不同的身体部位进行统一的参数自适应，导致稳定区域过适应、易偏移关节欠适应。为解决该问题，我们提出 TT-HA，一种新颖的测试时异构自适应方法，它隐式估计各解剖部位的域变化，并自适应调整相应参数。基于人体解剖学，TT-HA 利用基于 Fisher 信息矩阵的参数不确定性分析，将参数划分为五个解剖子集。测试阶段，TT-HA 使用实例归一化统计量与 Earth Mover's Distance（EMD）量化各部位的域变化，动态决定需要自适应哪些部位专属参数以及自适应的程度。当检测到显著域偏移时，TT-HA 仅将受影响的部位恢复为源域训练值，从而在无需全参数重置的情况下实现稳健自适应；轻微偏移则触发对应参数的微调，同时保持其余参数不变。实验表明，TT-HA 具有更优的全身精度，肢体误差下降幅度大于先前方法，验证了其面向解剖结构的针对性有效性。
英文原文摘要 1636 字符
The research frontier in human pose prediction (HPP) is advancing toward continual test-time adaptation (TTA), where models must self-adapt to dynamic test distributions. To date, the homeostatic continual TTA remains the sole viable solution, which isolates the model parameters and update domain-sensitive ones. Despite mitigating full-body domain gaps, human anatomical heterogeneity (domain shifts often localize to specific regions) is ignored. This anatomical-agnostic approach forces uniform parameter adaptation across kinematically distinct segments, causing: over-adaptation of stable regions and under-adaptation of shift-prone articulations. To address it, we introduce TT-HA, a novel Test-Time Heterogeneous Adaptation that implicitly estimates domain changes for anatomical segments, and adapt the corresponding parameters. Building on human anatomy, TT-HA partitions parameters into five anatomical subsets using fisher information matrix-based parameters uncertainty analysis. During testing, TT-HA uses the instance normalization statistics and Earth Mover's Distance (EMD) to quantify segment-wise domain changes, dynamically determining which segment-specific parameters to adapt and to what extent. When substantial domain shifts are detected, TT-HA restores only affected segments to source-trained values, ensuring robust adaptation without full parameter resetting; minor shifts trigger the fine-tuning of corresponding parameters while preserving remaining ones. Experiments show TT-HA's superior full-body accuracy with greater limb error decrease than prior methods, proving its anatomically-targeted efficacy.