Learning Deep Hierarchical Features with Spatial Regularization for One-Class Facial Expression Recognition
Bingjun Luo, Junjie Zhu, Tianyu Yang, Sicheng Zhao, Chao Hu, Xibin Zhao, Yue Gao
Abstract
Existing methods on facial expression recognition (FER) are mainly trained in the setting when multi-class data is available. However, to detect the alien expressions that are absent during training, this type of methods cannot work. To address this problem, we develop a Hierarchical Spatial One Class Facial Expression Recognition Network (HS-OCFER) which can construct the decision boundary of a given expression class (called normal class) by training on only one-class data. Specifically, HS-OCFER consists of three novel components. First, hierarchical bottleneck modules are proposed to enrich the representation power of the model and extract detailed feature hierarchy from different levels. Second, multi-scale spatial regularization with facial geometric information is employed to guide the feature extraction towards emotional facial representations and prevent the model from overfitting extraneous disturbing factors. Third, compact intra-class variation is adopted to separate the normal class from alien classes in the decision space. Extensive evaluations on 4 typical FER datasets from both laboratory and wild scenarios show that our method consistently outperforms state-of-the-art One-Class Classification (OCC) approaches.
BibTeX
@article{Luo_Zhu_Yang_Zhao_Hu_Zhao_Gao_2023, title={Learning Deep Hierarchical Features with Spatial Regularization for One-Class Facial Expression Recognition}, volume={37}, url={https://ojs.aaai.org/index.php/AAAI/article/view/25749}, DOI={10.1609/aaai.v37i5.25749}, abstractNote={Existing methods on facial expression recognition (FER) are mainly trained in the setting when multi-class data is available. However, to detect the alien expressions that are absent during training, this type of methods cannot work. To address this problem, we develop a Hierarchical Spatial One Class Facial Expression Recognition Network (HS-OCFER) which can construct the decision boundary of a given expression class (called normal class) by training on only one-class data. Specifically, HS-OCFER consists of three novel components. First, hierarchical bottleneck modules are proposed to enrich the representation power of the model and extract detailed feature hierarchy from different levels. Second, multi-scale spatial regularization with facial geometric information is employed to guide the feature extraction towards emotional facial representations and prevent the model from overfitting extraneous disturbing factors. Third, compact intra-class variation is adopted to separate the normal class from alien classes in the decision space. Extensive evaluations on 4 typical FER datasets from both laboratory and wild scenarios show that our method consistently outperforms state-of-the-art One-Class Classification (OCC) approaches.}, number={5}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Luo, Bingjun and Zhu, Junjie and Yang, Tianyu and Zhao, Sicheng and Hu, Chao and Zhao, Xibin and Gao, Yue}, year={2023}, month={Jun.}, pages={6065-6073} }