发表机构
Bernoulli Institute, University of Groningen（格罗宁根大学伯努利研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究表观面部年龄估计中模型与人类数据的不确定性，利用APPA - REAL数据集，通过三种贝叶斯神经网络近似方法训练模型，可输出预测年龄及两种不确定性量，证实不同来源不确定性可量化。
AI 中文摘要
从面部图像估计个体的表观年龄具有挑战性，因为感知具有主观性且数据存在固有变异性。我们研究不确定性估计的作用，将不确定性归因于知识缺乏（认知性）或固有噪声/偶然性（随机性）。利用APPA - REAL数据集，我们使用三种贝叶斯神经网络近似方法（MC - DropConnect、Flipout和深度集成）在不同大小的数据集上训练，利用该数据集中人类随机性不确定性的监督。每个模型输出预测的表观年龄以及随机性和认知性不确定性的量。结果证实，固有随机性不确定性在不同数据集大小下保持稳定，而认知性不确定性随训练数据减少而增加。这些发现表明在面部年龄估计中可以量化不同来源的不确定性。
英文摘要
Estimating the apparent age of individuals from facial images is challenging due to the subjective nature of perception and the inherent variability of the data. We investigate the role of uncertainty estimation, attributing uncertainty jointly to a lack of knowledge (epistemic) or inherent noise/chance (aleatoric). Leveraging the APPA-REAL dataset, we train Bayesian Neural Networks on datasets of varying sizes using three BNN approximations: MC-DropConnect, Flipout, and Deep Ensembles using supervision on human aleatoric uncertainty available in the APPA-REAL dataset. Each model outputs both the predicted apparent age and the amount of aleatoric and epistemic uncertainty. Our results confirm the hypothesis that the inherent aleatoric uncertainty remains stable across dataset sizes, while epistemic uncertainty increases as training data decreases. These findings demonstrate that different sources of uncertainty can be quantified in face age estimation.
Comments12 pages, 7 figures, ANNPR 2026 camera ready + appendix
