| Title | Towards a General Deep Feature Extractor for Facial Expression Recognition |
| Publication Type | Conference Paper |
| Year of Publication | 2021 |
| Authors | Schoneveld, Liam, Othmani, Alice |
| Conference Name | 2021 IEEE International Conference on Image Processing (ICIP) |
| Keywords | Conferences, Deep Learning, emotion recognition, face recognition, facial expression recognition, facial recognition, Human Behavior, image recognition, knowledge distillation, Metrics, model generalisation, pubcrawl, resilience, Resiliency, Training, Visual emotion recognition, visualization |
| Abstract | The human face conveys a significant amount of information. Through facial expressions, the face is able to communicate numerous sentiments without the need for verbalisation. Visual emotion recognition has been extensively studied. Recently several end-to-end trained deep neural networks have been proposed for this task. However, such models often lack generalisation ability across datasets. In this paper, we propose the Deep Facial Expression Vector ExtractoR (DeepFEVER), a new deep learning-based approach that learns a visual feature extractor general enough to be applied to any other facial emotion recognition task or dataset. DeepFEVER outperforms state-of-the-art results on the AffectNet and Google Facial Expression Comparison datasets. DeepFEVER's extracted features also generalise extremely well to other datasets - even those unseen during training - namely, the Real-World Affective Faces (RAF) dataset. |
| DOI | 10.1109/ICIP42928.2021.9506025 |
| Citation Key | schoneveld_towards_2021 |
Towards a General Deep Feature Extractor for Facial Expression Recognition