量化身体特征对识别模型的影响，揭示体重是关键因素
A Quantitative Evaluation of the Expressivity of BMI, Pose and Gender in Body Embeddings for Recognition and Identification
- 用二次神经网络测量特征与性别、姿态、体重的编码强度
- 体重在最终层表达力最高，姿态次之，性别最弱
- 适合关注公平性与模型可解释性的研究者参考
行人重识别（ReID）系统在跨图像或视频帧匹配个体中至关重要。然而，现有方法常受性别、姿态和身体质量指数（BMI）等属性影响，在非受限环境下变化显著，引发公平性和泛化能力的担忧。为此，我们扩展了表达力概念，即通过二级神经网络量化学习特征与特定属性之间的互信息。在三个ReID模型上应用该框架，发现BMI在最后层始终具有最高表达力，表明其在识别中的主导作用。在最后一层注意力机制中，属性表达力排序为：BMI > Pitch > Gender > Yaw，揭示其相对影响。表达力值随层和训练周期动态变化，反映属性编码过程。这些结果凸显身体属性在ReID中的核心作用，并建立了一种系统揭示属性驱动关联的方法。
原文摘要 · Abstract (English)
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.
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。