Towards a Scalable Identification of Novel Modes in Generative Models

arXiv:2405.02700v1 Announce Type: new
Abstract: An interpretable comparison of generative models requires the identification of sample types produced more frequently by each of the involved models. While several quantitative scores have been proposed in the literature to rank different generative models, such score-based evaluations do not reveal the nuanced differences between the generative models in capturing various sample types. In this work, we propose a method called Fourier-based Identification of Novel Clusters (FINC) to identify modes produced by a generative …

abstract arxiv comparison cs.cv cs.lg differences generative generative models identification literature novel quantitative sample scalable type types while