Feature Unlearning for Pre-trained GANs and VAEs

arXiv:2303.05699v4 Announce Type: replace-cross
Abstract: We tackle the problem of feature unlearning from a pre-trained image generative model: GANs and VAEs. Unlike a common unlearning task where an unlearning target is a subset of the training set, we aim to unlearn a specific feature, such as hairstyle from facial images, from the pre-trained generative models. As the target feature is only presented in a local region of an image, unlearning the entire image from the pre-trained model may result in …

abstract aim arxiv cs.cv cs.lg feature gans generative image images set training type unlearn unlearning