身体嵌入中BMI、姿态与性别对识别与身份鉴定表达力的定量评估
A Quantitative Evaluation of the Expressivity of BMI, Pose and Gender in Body Embeddings for Recognition and Identification
AI总结：
本文通过互信息框架定量评估ReID模型中BMI、姿态和性别的表达力，发现BMI在最终层和注意力层中影响最大，揭示了身体属性在行人重识别中的主导作用。
摘要：
行人重识别（ReID）系统能够在图像或视频帧之间匹配个体，在许多现实应用中至关重要。然而，现有方法往往受到性别、姿态和身体质量指数（BMI）等属性的影响，这些属性在无约束环境中变化，并引发与公平性和泛化性相关的担忧。为了解决这一问题，我们扩展了表达力的概念，将其定义为学习到的特征与特定属性之间的互信息，并使用一个次级神经网络来量化属性被编码的强度。将该框架应用于三个ReID模型后，我们发现BMI在最终层中始终表现出最高的表达力，表明其在识别中起主导作用。在最后一个注意力层中，属性排序为BMI > Pitch > Gender > Yaw，揭示了它们在表示学习中的相对影响。表达力值还随网络层和训练轮次变化，反映了属性编码的动态过程。这些发现证明了身体属性在ReID中的核心作用，并建立了一种揭示属性驱动相关性的原则性方法。
英文摘要：
Person Re-identification (ReID) systems that match individuals across images or video frames are essential in many real-world applications. However, existing methods are often influenced by attributes such as gender, pose, and body mass index (BMI), which vary in unconstrained settings and raise concerns related to fairness and generalization. To address this, we extend the notion of expressivity, defined as the mutual information between learned features and specific attributes, using a secondary neural network to quantify how strongly attributes are encoded. Applying this framework to three ReID models, we find that BMI consistently shows the highest expressivity in the final layers, indicating its dominant role in recognition. In the last attention layer, attributes are ranked as BMI > Pitch > Gender > Yaw, revealing their relative influences in representation learning. Expressivity values also evolve across layers and training epochs, reflecting a dynamic encoding of attributes. These findings demonstrate the central role of body attributes in ReID and establish a principled approach for uncovering attribute driven correlations.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
