Facial Attribute Classification (FAC) has attracted increasing attention in
computer vision and pattern recognition. However, state-of-the-art FAC methods
perform face detection/alignment and FAC independently. The inherent
dependencies between these tasks are not fully exploited. In addition, most
methods predict all facial attributes using the same CNN network architecture,
which ignores the different learning complexities of facial attributes. To
address the above problems, we propose a novel deep multi-task multi-label CNN,
termed DMM-CNN, for effective FAC. Specifically, DMM-CNN jointly optimizes two
closely-related tasks (i.e., facial landmark detection and FAC) to improve the
performance of FAC by taking advantage of multi-task learning. To deal with the
diverse learning complexities of facial attributes, we divide the attributes
into two groups: objective attributes and subjective attributes. Two different
network architectures are respectively designed to extract features for two
groups of attributes, and a novel dynamic weighting scheme is proposed to
automatically assign the loss weight to each facial attribute during training.
Furthermore, an adaptive thresholding strategy is developed to effectively
alleviate the problem of class imbalance for multi-label learning. Experimental
results on the challenging CelebA and LFWA datasets show the superiority of the
proposed DMM-CNN method compared with several state-of-the-art FAC methods.

本研究提出了一种新型的深度多任务多标签卷积神经网络（DMM-CNN），通过联合优化面部地标检测和面部属性分类两个紧密相关的任务以利用多任务学习来提高面部属性分类的性能，并针对不同的学习复杂性将面部属性分为两组，为两组属性设计不同的网络架构，并提出一种新的动态加权方案来自动分配损失权重。此外，还开发了一种自适应阈值策略来有效地缓解多标签学习的类别不平衡问题。实验结果表明，与几种最先进的 FAC 方法相比，所提出的 DMM-CNN 方法在具有挑战性的 CelebA 和 LFWA 数据集上具有优越性。