Attack Deterministic Conditional Image Generative Models for Diverse and Controllable Generation

arXiv:2403.08294v1 Announce Type: new
Abstract: Existing generative adversarial network (GAN) based conditional image generative models typically produce fixed output for the same conditional input, which is unreasonable for highly subjective tasks, such as large-mask image inpainting or style transfer. On the other hand, GAN-based diverse image generative methods require retraining/fine-tuning the network or designing complex noise injection functions, which is computationally expensive, task-specific, or struggle to generate high-quality results. Given that many deterministic conditional image generative models have been able …

abstract adversarial arxiv cs.cv diverse gan generative generative adversarial network generative models image inpainting network style style transfer tasks transfer type