真实健身房环境导致动作识别模型严重失效，且传统不确定性检测无效。
Severe Domain Shift in Skeleton-Based Action Recognition:A Study of Uncertainty Failure in Real-World Gym Environments
- 构建新数据集模拟真实场景的视角与风格变化，测试模型鲁棒性。
- 模型在真实环境上准确率从63.2%暴跌至1.6%，仍自信错误预测。
- 提出轻量级门控机制，让模型学会拒绝不确定判断，提升安全性。
从受控多视角3D骨骼捕捉到非约束单目2D姿态估计的实用部署过程中，存在复合领域偏移，其安全影响仍未被充分探讨。我们通过新构建的Gym2D数据集（风格/视角偏移）和UCF101数据集（语义偏移），系统研究了这一严重域偏移问题。所提出的骨架变换器在NTU-120上跨主体准确率为63.2%，但在零样本迁移至健身房域时降至1.6%，在UCF101上为1.16%。关键发现：高外分布检测AUROC并不保证安全选择性分类。标准不确定性方法无法检测性能下降：即使在50%覆盖率下，模型仍有99.6%的误判风险。尽管基于能量的评分（AUROC ≥ 0.91）和马氏距离能提供可靠分布检测信号，但其风险-覆盖率表现仍差。引入轻量级微调门控机制可恢复校准性，实现优雅拒答，显著降低自信错误预测率。本工作挑战了主流部署假设，为语义与几何骨架识别部署提供了原则性安全分析。
原文摘要 · Abstract (English)
The practical deployment gap -- transitioning from controlled multi-view 3D skeleton capture to unconstrained monocular 2D pose estimation -- introduces a compound domain shift whose safety implications remain critically underexplored. We present a systematic study of this severe domain shift using a novel Gym2D dataset (style/viewpoint shift) and the UCF101 dataset (semantic shift). Our Skeleton Transformer achieves 63.2% cross-subject accuracy on NTU-120 but drops to 1.6% under zero-shot transfer to the Gym domain and 1.16% on UCF101. Critically, we demonstrate that high Out-Of-Distribution (OOD) detection AUROC does not guarantee safe selective classification. Standard uncertainty methods fail to detect this performance drop: the model remains confidently incorrect with 99.6% risk even at 50% coverage across both OOD datasets. While energy-based scoring (AUROC >= 0.91) and Mahalanobis distance provide reliable distributional detection signals, such high AUROC scores coexist with poor risk-coverage behavior when making decisions. A lightweight finetuned gating mechanism restores calibration and enables graceful abstention, substantially reducing the rate of confident wrong predictions. Our work challenges standard deployment assumptions, providing a principled safety analysis of both semantic and geometric skeleton recognition deployment.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。