Generative Active Learning for Image Synthesis Personalization

arXiv:2403.14987v1 Announce Type: new
Abstract: This paper presents a pilot study that explores the application of active learning, traditionally studied in the context of discriminative models, to generative models. We specifically focus on image synthesis personalization tasks. The primary challenge in conducting active learning on generative models lies in the open-ended nature of querying, which differs from the closed form of querying in discriminative models that typically target a single concept. We introduce the concept of anchor directions to transform …

active learning arxiv cs.cv generative image personalization synthesis type