针对人脸年龄估计中的标签模糊问题，提出分阶段自适应标签分布学习方法。
Stage-wise Adaptive Label Distribution for Facial Age Estimation
- 按年龄阶段动态建模标签模糊性，改进传统固定邻近关系的标签分布学习。
- 在MORPH-II和FG-NET数据集上分别达到1.74和2.15的平均绝对误差。
- 适用于对年龄估计精度要求高的实际场景，如人脸识别与安防系统。
标签模糊性是年龄估计任务中的主要挑战。现有方法通常通过标签分布学习建模相邻年龄组间的相关性，但忽略了不同年龄阶段间模糊程度的差异。本文提出分阶段自适应标签分布学习（SA-LDL）算法，基于锚点与所有其他年龄嵌入相似性的分析，发现标签模糊具有明显的阶段特征。通过联合采用分阶段自适应方差建模与加权损失函数，有效捕捉标签模糊的复杂结构，提升估计准确性与鲁棒性。大量实验表明，SA-LDL在MORPH-II和FG-NET数据集上分别取得1.74和2.15的平均绝对误差（MAE），表现优异。
原文摘要 · Abstract (English)
Label ambiguity poses a significant challenge in age estimation tasks. Most existing methods address this issue by modeling correlations between adjacent age groups through label distribution learning. However, they often overlook the varying degrees of ambiguity present across different age stages. In this paper, we propose a Stage-wise Adaptive Label Distribution Learning (SA-LDL) algorithm, which leverages the observation -- revealed through our analysis of embedding similarities between an anchor and all other ages -- that label ambiguity exhibits clear stage-wise patterns. By jointly employing stage-wise adaptive variance modeling and weighted loss function, SA-LDL effectively captures the complex and structured nature of label ambiguity, leading to more accurate and robust age estimation. Extensive experiments demonstrate that SA-LDL achieves competitive performance, with MAE of 1.74 and 2.15 on the MORPH-II and FG-NET datasets.
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。