Skip to content

Face Recognition with Knowledge Distillation from Synthetic Data


Training face recognition models also requires large identity-labeled datasets. Meanwhile, there are privacy and ethical concerns with collecting and using large face recognition datasets. While generating synthetic datasets for training face recognition models is an alternative option, it is challenging to generate synthetic data with sufficient intra-class variations. In addition, there is still a considerable gap between the performance of models trained on real and synthetic data.

We proposed a new framework (named SynthDistill) to train lightweight face recognition models by distilling the knowledge of a pretrained teacher face recognition model using synthetic data.


Krivokuca, V. and Otroshi Shahreza, H. and George, A. and Marcel, S. (2023). SynthDistill: Face Recognition with Knowledge Distillation from Synthetic Data. IEEE International Joint Conference on Biometrics (IJCB 2023).


We use a pretrained face generator network to generate synthetic face images and use the synthesized images to learn a lightweight student network. We use synthetic face images without identity labels, mitigating the problems in the intra-class variation generation of synthetic datasets. The results on five different face recognition datasets demonstrate the superiority of our lightweight model compared to models trained on previous synthetic datasets, achieving a verification accuracy of 99.52% on the LFW dataset with a lightweight network. The results also show that our proposed framework significantly reduces the gap between training with real and synthetic data.


  • Face Recognition

Technology Readiness Level



SynthDistill - Step 1: Faces images are generated with StyleGAN. Step 2: More challenging samples are generated based on the teacher-student agreement. The student model is updated based on the distillation loss while all other network blocks remains frozen.

Contact us for more information

  • Interested in using our technologies?
  • Interested to know more about the licensing possibilities and conditions?

Contact us