Class-Prototype Conditional Diffusion Model with Gradient Projection for Continual Learning

arXiv:2312.06710v3 Announce Type: replace
Abstract: Mitigating catastrophic forgetting is a key hurdle in continual learning. Deep Generative Replay (GR) provides techniques focused on generating samples from prior tasks to enhance the model's memory capabilities using generative AI models ranging from Generative Adversarial Networks (GANs) to the more recent Diffusion Models (DMs). A major issue is the deterioration in the quality of generated data compared to the original, as the generator continuously self-learns from its outputs. This degradation can lead to …

abstract adversarial ai models arxiv capabilities catastrophic forgetting class continual cs.lg diffusion diffusion model diffusion models gans generative generative adversarial networks generative ai models gradient key memory networks prior projection samples tasks type