Sparse deep feature learning for facial expression recognition

作者：

Highlights：

• A new framework of facial expression recognition is proposed, where different feature sparseness strategies are embedded in deep networks and further investigated.

• Feature sparseness of the fully-connected layer input is embedded into a deep network to boost the feature generalization ability, which includes less parameters, while achieves better performance than other network sparseness.

• The advantage of the feature sparseness is evaluated with a toy model based on a quantitative metric.

• The deep metric learning achieved competitive recognition rates and state-of-the-art cross-database performance on four benchmark expression databases, i.e. FER2013, CK+, Oulu-CASIA and MMI.

摘要

•A new framework of facial expression recognition is proposed, where different feature sparseness strategies are embedded in deep networks and further investigated.•Feature sparseness of the fully-connected layer input is embedded into a deep network to boost the feature generalization ability, which includes less parameters, while achieves better performance than other network sparseness.•The advantage of the feature sparseness is evaluated with a toy model based on a quantitative metric.•The deep metric learning achieved competitive recognition rates and state-of-the-art cross-database performance on four benchmark expression databases, i.e. FER2013, CK+, Oulu-CASIA and MMI.

论文关键词：Expression recognition,Feature sparseness,Deep metric learning,Fine tuning,Generalization capability

论文评审过程：Received 16 August 2018, Revised 6 May 2019, Accepted 11 July 2019, Available online 12 July 2019, Version of Record 16 July 2019.

论文官网地址：https://doi.org/10.1016/j.patcog.2019.106966