Mode-Aware Continual Learning for Conditional Generative Adversarial Networks
This work addresses the problem of catastrophic forgetting in generative models for researchers and practitioners, offering an incremental improvement in continual learning techniques.
The paper tackles the challenge of continual learning for conditional generative adversarial networks by introducing a mode-aware approach that uses a mode-affinity score to learn new target modes with limited samples while preserving existing ones, achieving gains over state-of-the-art methods with fewer training samples.
The main challenge in continual learning for generative models is to effectively learn new target modes with limited samples while preserving previously learned ones. To this end, we introduce a new continual learning approach for conditional generative adversarial networks by leveraging a mode-affinity score specifically designed for generative modeling. First, the generator produces samples of existing modes for subsequent replay. The discriminator is then used to compute the mode similarity measure, which identifies a set of closest existing modes to the target. Subsequently, a label for the target mode is generated and given as a weighted average of the labels within this set. We extend the continual learning model by training it on the target data with the newly-generated label, while performing memory replay to mitigate the risk of catastrophic forgetting. Experimental results on benchmark datasets demonstrate the gains of our continual learning approach over the state-of-the-art methods, even when using fewer training samples.