@article{632d127e3c924acaa1ef45e8a533283c,
title = "Evaluation Metrics for Conditional Image Generation",
abstract = "We present two new metrics for evaluating generative models in the class-conditional image generation setting. These metrics are obtained by generalizing the two most popular unconditional metrics: the Inception Score (IS) and the Fr{\'e}chet Inception Distance (FID). A theoretical analysis shows the motivation behind each proposed metric and links the novel metrics to their unconditional counterparts. The link takes the form of a product in the case of IS or an upper bound in the FID case. We provide an extensive empirical evaluation, comparing the metrics to their unconditional variants and to other metrics, and utilize them to analyze existing generative models, thus providing additional insights about their performance, from unlearned classes to mode collapse.",
keywords = "Conditional generation, Evaluation metrics, Fr{\'e}chet Inception Distance, Image generation, Inception Score",
author = "Yaniv Benny and Tomer Galanti and Sagie Benaim and Lior Wolf",
note = "Publisher Copyright: {\textcopyright} 2021, The Author(s).",
year = "2021",
month = may,
doi = "10.1007/s11263-020-01424-w",
language = "אנגלית",
volume = "129",
pages = "1712--1731",
journal = "International Journal of Computer Vision",
issn = "0920-5691",
publisher = "Springer Netherlands",
number = "5",
}