Task-Oriented Feature-Fused Network With Multivariate Dataset for Joint Face Analysis
Task-Oriented Feature-Fused Network With Multivariate Dataset for Joint Face Analysis
复制标题
用于联合人脸分析的具有多元数据集的面向任务的特征融合网络
DOI：
10.1109/tcyb.2019.2917049
复制
发表时间：
2020-03-01
影响因子：
11.8
通讯作者：
Li, Stan Z.
中科院分区：
文献类型：
--
作者：
Lin, Xuxin;Wan, Jun;Li, Stan Z.
人脸分析的深度多任务学习越来越受到人们的关注。从文献来看，现有的方法大多是通过联合学习多个辅助任务来优化一个主任务。由于以下原因，在多任务框架中考虑每个任务的性能是具有挑战性的：1)不同的人脸任务通常依赖于不同层次的语义特征；2)每个任务的学习收敛速度不同，会影响联合训练时的整体表现；3)多任务模型需要丰富的标签信息来进行高效训练，但现有的人脸数据集提供的标注有限。为了解决这些问题，我们提出了一种面向任务的特征融合网络（TFN），用于同时解决人脸检测、地标定位和属性分析问题。在该网络中，设计了面向任务的特征融合块来学习特定任务的特征组合；然后，提出了一种备选的多任务训练方案，考虑每个任务的不同学习能力对每个任务进行优化。我们还提供了一个名为JFA的大规模人脸数据集来支持所提出的方法，该方法提供了多变量标签，包括人脸边界框、68个面部地标和3个属性标签（即表观年龄、性别和种族）。实验结果表明，TFN在JFA数据集上优于多个多任务模型。此外，我们的方法在WIDER FACE和300W数据集上取得了具有竞争力的表现，并在MORPH II数据集上获得了最先进的性别识别结果。
Deep multitask learning for face analysis has received increasing attentions. From literature, most existing methods focus on optimizing a main task by jointly learning several auxiliary tasks. It is challenging to consider the performance of each task in a multitask framework due to the following reasons: 1) different face tasks usually rely on different levels of semantic features; 2) each task has different learning convergence rate, which could affect the whole performance when joint training; and 3) multitask model needs rich label information for efficient training, but existing facial datasets provide limited annotations. To address these issues, we propose a task-oriented feature-fused network (TFN) for simultaneously solving face detection, landmark localization, and attribute analysis. In this network, a task-oriented feature-fused block is designed to learn task-specific feature combinations; then, an alternative multitask training scheme is presented to optimize each task with considering of their different learning capacities. We also present a large-scale face dataset called JFA in support of proposed method, which provides multivariate labels, including face bounding box, 68 facial landmarks, and 3 attribute labels (i.e., apparent age, gender, and ethnicity). The experimental results suggest that the TFN outperforms several multitask models on the JFA dataset. Furthermore, our approach achieves competitive performances on WIDER FACE and 300W dataset, and obtains state-of-the-art results for gender recognition on the MORPH II dataset.