FAN-Face: a Simple Orthogonal Improvement to Deep Face Recognition


  • Jing Yang University of Nottingham
  • Adrian Bulat Samsung AI Center, Cambridge
  • Georgios Tzimiropoulos University of Nottingham, Samsung AI Center, Cambridge



It is known that facial landmarks provide pose, expression and shape information. In addition, when matching, for example, a profile and/or expressive face to a frontal one, knowledge of these landmarks is useful for establishing correspondence which can help improve recognition. However, in prior work on face recognition, facial landmarks are only used for face cropping in order to remove scale, rotation and translation variations. This paper proposes a simple approach to face recognition which gradually integrates features from different layers of a facial landmark localization network into different layers of the recognition network. To this end, we propose an appropriate feature integration layer which makes the features compatible before integration. We show that such a simple approach systematically improves recognition on the most difficult face recognition datasets, setting a new state-of-the-art on IJB-B, IJB-C and MegaFace datasets.




How to Cite

Yang, J., Bulat, A., & Tzimiropoulos, G. (2020). FAN-Face: a Simple Orthogonal Improvement to Deep Face Recognition. Proceedings of the AAAI Conference on Artificial Intelligence, 34(07), 12621-12628.



AAAI Technical Track: Vision