English

Continual Learning of Personalized Generative Face Models with Experience Replay

Computer Vision and Pattern Recognition 2024-12-04 v1

Abstract

We introduce a novel continual learning problem: how to sequentially update the weights of a personalized 2D and 3D generative face model as new batches of photos in different appearances, styles, poses, and lighting are captured regularly. We observe that naive sequential fine-tuning of the model leads to catastrophic forgetting of past representations of the individual's face. We then demonstrate that a simple random sampling-based experience replay method is effective at mitigating catastrophic forgetting when a relatively large number of images can be stored and replayed. However, for long-term deployment of these models with relatively smaller storage, this simple random sampling-based replay technique also forgets past representations. Thus, we introduce a novel experience replay algorithm that combines random sampling with StyleGAN's latent space to represent the buffer as an optimal convex hull. We observe that our proposed convex hull-based experience replay is more effective in preventing forgetting than a random sampling baseline and the lower bound.

Keywords

Cite

@article{arxiv.2412.02627,
  title  = {Continual Learning of Personalized Generative Face Models with Experience Replay},
  author = {Annie N. Wang and Luchao Qi and Roni Sengupta},
  journal= {arXiv preprint arXiv:2412.02627},
  year   = {2024}
}

Comments

Accepted to WACV 2025. Project page (incl. supplementary materials): https://anniedde.github.io/personalizedcontinuallearning.github.io/

R2 v1 2026-06-28T20:21:40.778Z