2021
DOI: 10.48550/arxiv.2103.11521
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Conditional Frechet Inception Distance

Abstract: We consider distance functions between conditional distributions functions. We focus on the Wasserstein metric and its Gaussian case known as the Frechet Inception Distance (FID). We develop conditional versions of these metrics, and analyze their relations. Then, we numerically compare the metrics in the context of performance evaluation of conditional generative models. Our results show that the metrics are similar in classical models which are less susceptible to conditional collapse. But the conditional di… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
5
0

Year Published

2021
2021
2023
2023

Publication Types

Select...
2
2
1

Relationship

0
5

Authors

Journals

citations
Cited by 5 publications
(5 citation statements)
references
References 26 publications
0
5
0
Order By: Relevance
“…5. The Flechet inception distance (FID) 30 is then used for the discrimination. Experiments: we evaluate our proposed anomaly detection technique on a NDT industrial dataset and the MVTec dataset.…”
Section: Discussionmentioning
confidence: 99%
“…5. The Flechet inception distance (FID) 30 is then used for the discrimination. Experiments: we evaluate our proposed anomaly detection technique on a NDT industrial dataset and the MVTec dataset.…”
Section: Discussionmentioning
confidence: 99%
“…We report results for several different metrics, including peak-signal-to-noise ratio (PSNR), structural-similarity index (SSIM) (Wang et al, 2004), Fréchet Inception Score (FID) (Heusel et al, 2017), and conditional FID (cFID) (Soloveitchik et al, 2021). PSNR and SSIM were computed on the average of P posterior samples {i p } P p=1 , i.e.,…”
Section: Discussionmentioning
confidence: 99%
“…The Fréchet Inception Distance (FID) is a metric used to evaluate the quality of images generated by a generative model. Specifically, this criterion has been developed for assessing the performance of GANs [51]. FID calculates the distance between feature vectors of real and generated (fake) images produced by the generative model.…”
Section: Fréchet Inception Distance (Fid)mentioning
confidence: 99%
“…FID calculates the distance between feature vectors of real and generated (fake) images produced by the generative model. A low FID value indicates that the quality of the generated images by the generative model is higher and more similar to real images [51]. The FID results for different image datasets are recorded in Table 10.…”
Section: Fréchet Inception Distance (Fid)mentioning
confidence: 99%