Evaluation Metrics for Conditional Image Generation

Author:

Benny YanivORCID,Galanti Tomer,Benaim Sagie,Wolf Lior

Abstract

AbstractWe 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 Fréchet 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.

Publisher

Springer Science and Business Media LLC

Subject

Artificial Intelligence,Computer Vision and Pattern Recognition,Software

Reference29 articles.

1. Arjovsky, M., Chintala, S., & Bottou, L. (2017). Wasserstein generative adversarial networks. In D. Precup, & Y. W. Teh (Eds.), Proceedings of the 34th international conference on machine learning, proceedings of machine learning research (Vol. 70, pp. 214–223). PMLR, International Convention Centre, Sydney, Australia.

2. Bińkowski, M., Sutherland, D. J., Arbel, M., & Gretton, A. (2018). Demystifying mmd gans. arXiv preprint arXiv:1801.01401.

3. Brock, A., Donahue, J., & Simonyan, K. (2019). Large scale GAN training for high fidelity natural image synthesis. In International conference on learning representations. https://openreview.net/forum?id=B1xsqj09Fm

4. Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., & Abbeel, P. (2016). Infogan: interpretable representation learning by information maximizing generative adversarial nets. In Advances in neural information processing systems (pp. 2172–2180).

5. Dowson, D. C., & Landau, B. V. (1982). The fréchet distance between multivariate normal distributions. Journal of Multivariate Analysis, 12(3), 450–455.

Cited by 23 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3