系统评估外观步态识别在真实场景下的鲁棒性，发现提取器偏差影响显著。
RobustGait: Robustness Analysis for Appearance Based Gait Recognition
- 构建四维鲁棒性评测框架，涵盖扰动类型与模型架构
- 15种噪声在5级强度下测试，发现RGB层噪声更贴近真实退化
- 揭示提取器偏差是关键瓶颈，适合部署优化研究者参考
基于外观的步态识别在受控数据集上表现强劲，但对其在真实世界干扰和轮廓变异下的鲁棒性缺乏系统评估。我们提出RobustGait，一个细粒度的鲁棒性评估框架，覆盖四种维度：扰动类型（数字、环境、时间、遮挡）、轮廓提取方法（分割与解析网络）、步态识别模型架构能力及多种部署场景。基准测试包含15种腐蚀类型，共5个严重等级，覆盖CASIA-B、CCPG、SUSTech1K三个数据集，并在MEVID进行野外验证，评估了六种前沿步态系统。研究发现：首先，RGB层级施加噪声更能反映真实退化，揭示畸变如何通过轮廓提取传递至下游识别系统；其次，步态识别准确率对轮廓提取器偏差高度敏感，暴露出被忽视的基准偏差来源；第三，鲁棒性同时依赖于扰动类型与模型结构设计；最后，探索了增强策略，表明噪声感知训练与知识蒸馏可提升性能，推动系统向可部署演进。代码已公开于https://reeshoon.github.io/robustgaitbenchmark。
原文摘要 · Abstract (English)
Appearance-based gait recognition have achieved strong performance on controlled datasets, yet systematic evaluation of its robustness to real-world corruptions and silhouette variability remains lacking. We present RobustGait, a framework for fine-grained robustness evaluation of appearance-based gait recognition systems. RobustGait evaluation spans four dimensions: the type of perturbation (digital, environmental, temporal, occlusion), the silhouette extraction method (segmentation and parsing networks), the architectural capacities of gait recognition models, and various deployment scenarios. The benchmark introduces 15 corruption types at 5 severity levels across CASIA-B, CCPG, and SUSTech1K, with in-the-wild validation on MEVID, and evaluates six state-of-the-art gait systems. We came across several exciting insights. First, applying noise at the RGB level better reflects real-world degradation, and reveal how distortions propagate through silhouette extraction to the downstream gait recognition systems. Second, gait accuracy is highly sensitive to silhouette extractor biases, revealing an overlooked source of benchmark bias. Third, robustness is dependent on both the type of perturbation and the architectural design. Finally, we explore robustness-enhancing strategies, showing that noise-aware training and knowledge distillation improve performance and move toward deployment-ready systems. Code is available at https://reeshoon.github.io/robustgaitbenchmark
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。