CFTS-GAN: Continual Few-Shot Teacher Student for Generative Adversarial Networks
This addresses the problem of training GANs with limited data across multiple tasks for researchers in generative models, though it appears incremental as it builds on existing teacher-student and distillation techniques.
The paper tackled the combined challenges of catastrophic forgetting and overfitting in GANs for few-shot continual learning, proposing CFTS-GAN, which achieved more diverse image synthesis and competitive performance with state-of-the-art models.
Few-shot and continual learning face two well-known challenges in GANs: overfitting and catastrophic forgetting. Learning new tasks results in catastrophic forgetting in deep learning models. In the case of a few-shot setting, the model learns from a very limited number of samples (e.g. 10 samples), which can lead to overfitting and mode collapse. So, this paper proposes a Continual Few-shot Teacher-Student technique for the generative adversarial network (CFTS-GAN) that considers both challenges together. Our CFTS-GAN uses an adapter module as a student to learn a new task without affecting the previous knowledge. To make the student model efficient in learning new tasks, the knowledge from a teacher model is distilled to the student. In addition, the Cross-Domain Correspondence (CDC) loss is used by both teacher and student to promote diversity and to avoid mode collapse. Moreover, an effective strategy of freezing the discriminator is also utilized for enhancing performance. Qualitative and quantitative results demonstrate more diverse image synthesis and produce qualitative samples comparatively good to very stronger state-of-the-art models.