Identity-Enhanced Network for Facial Expression Recognition

Abstract

Facial expression recognition is a challenging task, arguably because of large intra-class variations and high inter-class similarities. The core drawback of the existing approaches is the lack of ability to discriminate the changes in appearance caused by emotions and identities. In this paper, we present a novel identity-enhanced network (IDEnNet) to eliminate the negative impact of identity factor and focus on recognizing facial expressions. Spatial fusion combined with self-constrained multi-task learning are adopted to jointly learn the expression representations and identity-related information. We evaluate our approach on three popular datasets, namely Oulu-CASIA, CK+ and MMI. IDEnNet improves the baseline consistently, and achieves the best or comparable state-of-the-art on all three datasets.

Novel deep learning model for facial expression recognition based on maximum boosted CNN and LSTM

“…Fathallah et al [36] proposed a novel architecture to improve the classification accuracy by fine‐tuning the parameters. Li et al [37] presented an identity‐enhanced network (IDEnNet) to avoid negative identity impact and learns the informative features. Due to limited training data, the authors proposed a model which combines CNN with other deep learning network and used data augmentation to achieve greater performance.…”