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 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.
Original language | English |
---|---|
Pages (from-to) | 1712-1731 |
Number of pages | 20 |
Journal | International Journal of Computer Vision |
Volume | 129 |
Issue number | 5 |
DOIs | |
State | Published - May 2021 |
Externally published | Yes |
Bibliographical note
Publisher Copyright:© 2021, The Author(s).
Keywords
- Conditional generation
- Evaluation metrics
- Fréchet Inception Distance
- Image generation
- Inception Score