基于分层注意力的年龄估计与偏差估计
Hierarchical Attention-based Age Estimation and Bias Estimation
AI总结：
提出一种结合注意力双重增强聚合与概率分层回归的人脸年龄估计方法，在 MORPH II 上达到新的最先进准确率，并分析估计偏差。
摘要：
在本工作中，我们提出了一种基于人脸图像进行年龄估计的新型深度学习方法。我们首先介绍一种基于注意力的双重图像增强-聚合方法。这使网络能够联合利用多个人脸图像增强结果，其嵌入由 Transformer-Encoder 进行聚合。结果表明，所得聚合嵌入能够更好地编码人脸图像属性。随后，我们提出一个概率分层回归框架，该框架将年龄标签的离散概率估计与相应的回归器集成相结合。每个回归器都经过专门适配和训练，以在一个年龄范围内细化概率估计。实验表明，当应用于用于年龄估计的 MORPH II 数据集时，我们的方案优于同期方案，并提供了新的最先进年龄估计准确率。最后，我们对最先进的年龄估计结果进行了偏差分析。
英文摘要：
In this work we propose a novel deep-learning approach for age estimation based on face images. We first introduce a dual image augmentation-aggregation approach based on attention. This allows the network to jointly utilize multiple face image augmentations whose embeddings are aggregated by a Transformer-Encoder. The resulting aggregated embedding is shown to better encode the face image attributes. We then propose a probabilistic hierarchical regression framework that combines a discrete probabilistic estimate of age labels, with a corresponding ensemble of regressors. Each regressor is particularly adapted and trained to refine the probabilistic estimate over a range of ages. Our scheme is shown to outperform contemporary schemes and provide a new state-of-the-art age estimation accuracy, when applied to the MORPH II dataset for age estimation. Last, we introduce a bias analysis of state-of-the-art age estimation results.
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。
