A Flatter Loss for Bias Mitigation in Cross-dataset Facial Age Estimation
A Flatter Loss for Bias Mitigation in Cross-dataset Facial Age Estimation
复制标题
DOI：
10.1109/icpr48806.2021.9413134
复制
发表时间：
2020-10
期刊：
影响因子：
--
通讯作者：
A. Akbari;Muhammad Awais;Zhenhua Feng;Ammarah Farooq;J. Kittler
中科院分区：
文献类型：
--
作者：
A. Akbari;Muhammad Awais;Zhenhua Feng;Ammarah Farooq;J. Kittler
现有的面部年龄估计研究大多假设训练图像和测试图像是在相似的拍摄条件下拍摄的。然而，这在现实世界的应用程序中很少有效，其中训练集和测试集通常具有不同的特征。在本文中，我们提倡一个跨数据集协议的年龄估计基准。为了提高跨数据集年龄估计的性能，我们减轻了由学习算法本身引起的固有偏差。为此，我们提出了一种新的损失函数，它对神经网络训练更有效。所提出的损失函数的相对平滑性是其相对于通过随机梯度下降（SGD）执行的优化过程的优势。与现有的损失函数相比，建议的损失函数的梯度较低，导致SGD收敛到一个更好的最优点，从而更好的推广。跨数据集的实验结果表明，所提出的方法的优越性，在准确性和泛化能力方面的最先进的算法。
The most existing studies in the facial age estimation assume training and test images are captured under similar shooting conditions. However, this is rarely valid in real-worlds applications, where training and test sets usually have different characteristics. In this paper, we advocate a cross-dataset protocol for age estimation benchmarking. In order to improve the cross-dataset age estimation performance, we mitigate the inherent bias caused by the learning algorithm itself. To this end, we propose a novel loss function that is more effective for neural network training. The relative smoothness of the proposed loss function is its advantage with regards to the optimisation process performed by stochastic gradient descent (SGD). Compared with existing loss functions, the lower gradient of the proposed loss function leads to the convergence of SGD to a better optimum point, and consequently a better generalisation. The cross-dataset experimental results demonstrate the superiority of the proposed method over the state-of-the-art algorithms in terms of accuracy and generalisation capability.