良、优与最佳：通过属性感知学习提高面部嵌入的辨别能力
The Good, the Better, and the Best: Improving the Discriminability of Face Embeddings through Attribute-aware Learning
AI总结：
本文提出通过身份标签和相关面部属性指导学习，提升面部嵌入的辨别能力，实验表明使用身份相关属性子集和强制去除非身份相关属性能显著提升性能。
摘要：
尽管面部识别取得进展，但年龄、姿态和遮挡变化仍具挑战性。常用策略是通过面部属性辅助监督引导表示学习，促使视觉编码器关注身份相关区域。然而，现有方法通常依赖异质且固定的属性集，隐含假设属性相关性相同。本文提出属性感知面部识别架构，通过身份类别标签、身份相关面部属性和非身份相关属性监督学习面部嵌入。面部属性被组织成可解释的组别，使可分解和分析其个体贡献。实验表明，联合学习身份和面部属性可提升嵌入辨别能力，主要结论为：(i) 使用身份相关属性子集优于更广属性集；(ii) 显式强制嵌入去除非身份相关属性可进一步提升性能。此外，该方法可作为评估面部识别编码器可信度的诊断工具，通过测量抑制非身份相关属性后的准确率提升，提示存在冗余属性相关的捷径学习。
英文摘要：
Despite recent advances in face recognition, robust performance remains challenging under large variations in age, pose, and occlusion. A common strategy to address these issues is to guide representation learning with auxiliary supervision from facial attributes, encouraging the visual encoder to focus on identity-relevant regions. However, existing approaches typically rely on heterogeneous and fixed sets of attributes, implicitly assuming equal relevance across attributes. This assumption is suboptimal, as different attributes exhibit varying discriminative power for identity recognition, and some may even introduce harmful biases. In this paper, we propose an attribute-aware face recognition architecture that supervises the learning of facial embeddings using identity class labels, identity-relevant facial attributes, and non-identity-related attributes. Facial attributes are organized into interpretable groups, making it possible to decompose and analyze their individual contributions in a human-understandable manner. Experiments on standard face verification benchmarks demonstrate that joint learning of identity and facial attributes improves the discriminability of face embeddings with two major conclusions: (i) using identity-relevant subsets of facial attributes consistently outperforms supervision with a broader attribute set, and (ii) explicitly forcing embeddings to unlearn non-identity-related attributes yields further performance gains compared to leaving such attributes unsupervised. Additionally, our method serves as a diagnostic tool for assessing the trustworthiness of face recognition encoders by allowing for the measurement of accuracy gains with suppression of non-identity-relevant attributes, with such gains suggesting shortcut learning from redundant attributes associated with each identity.
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。
