Deep learning based facial expression recognition becomes more successful in many applications. However, the lack of labeled data is still a bottleneck for better recognition performance. Thus, it is of practical significance to exploit the rich unlabeled data for training deep neural networks (DNNs). In this paper, we propose a novel discriminative deep association learning (DDAL) framework. The unlabeled data is provided to train the DNNs with the labeled data simultaneously, in a multi-loss deep network based on association learning. Moreover, the discrimination loss is also utilized to ensure intra-class clustering and inter-class centers separating. Furthermore, a large synthetic facial expression dataset is generated and used as unlabeled data. By exploiting association learning mechanism on two facial expression datasets, competitive results are obtained. By utilizing synthetic data, the performance is increased clearly.

中文翻译：

---

区分性深度联想学习的面部表情识别

基于深度学习的面部表情识别在许多应用中变得更加成功。但是，缺少标记数据仍然是更好的识别性能的瓶颈。因此，利用丰富的未标记数据来训练深度神经网络（DNN）具有实际意义。在本文中，我们提出了一种新颖的区分性深度关联学习（DDAL）框架。在基于关联学习的多损失深度网络中，提供未标记数据以同时训练带有标记数据的DNN。此外，区分损失还用于确保类内聚类和类间中心分离。此外，将生成大型的合成面部表情数据集并将其用作未标记的数据。通过利用两个面部表情数据集上的关联学习机制，获得竞争结果。通过利用综合数据，可以明显提高性能。