论文标题
适应性面部年龄估计的自适应均值损失
Adaptive Mean-Residue Loss for Robust Facial Age Estimation
论文作者
论文摘要
自动化的面部年龄估计在多媒体分析中具有不同的现实应用，例如视频监视和人类计算机相互作用。但是，由于衰老过程的随机性和模棱两可，年龄评估具有挑战性。关于该主题的大多数研究工作都将任务视为年龄回归，分类和排名问题之一，并且不能很好地利用年龄分布来代表年龄歧义的标签。在这项工作中，我们提出了通过分布学习（即适应性均值弥补损失）的稳健面部年龄估计的简单而有效的损失函数，其中平均损失损失了估计年龄分布的平均值与基地真实年龄之间的差异，而残留损失损失了分布中动态top-k的entropy损失。数据集FG-NET和CLAP2016的实验结果验证了拟议损失的有效性。我们的代码可从https://github.com/jacobzhaoziyuan/amr-loss获得。
Automated facial age estimation has diverse real-world applications in multimedia analysis, e.g., video surveillance, and human-computer interaction. However, due to the randomness and ambiguity of the aging process, age assessment is challenging. Most research work over the topic regards the task as one of age regression, classification, and ranking problems, and cannot well leverage age distribution in representing labels with age ambiguity. In this work, we propose a simple yet effective loss function for robust facial age estimation via distribution learning, i.e., adaptive mean-residue loss, in which, the mean loss penalizes the difference between the estimated age distribution's mean and the ground-truth age, whereas the residue loss penalizes the entropy of age probability out of dynamic top-K in the distribution. Experimental results in the datasets FG-NET and CLAP2016 have validated the effectiveness of the proposed loss. Our code is available at https://github.com/jacobzhaoziyuan/AMR-Loss.
