On Self-Supervised Image Representations for GAN Evaluation

By Stanislav Morozov, Andrey Voynov, Artem Babenko. 2021

44 citations recorded by the source corpus.

Subfields: Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Representation & Self-Supervised Learning

1. Andreas Geiger
2. Timo Aila
3. Miika Aittala
4. Jens Muller
5. Tero Karras
6. Kashyap Chitta
7. Ali Borji
8. Axel Sauer

Citations in the corpus

• Projected GANs Converge Faster (2021, methodology): “Morozov et al. [53] show that in some cases, SwAV-FID is more consistent with human judgment of visual quality than FID.”
• The Role of ImageNet Classes in Fréchet Inception Distance (2022, methodology): “Furthermore, several authors (Karras et al., 2020b; Morozov et al., 2021; Nash et al., 2021; Borji, 2022; Alfarra et al., 2022) observe that there exists a discrepancy in the model ranking between human judgement and FID in non-ImageNet data, and proceed to introduce alternative metrics.”
• Pros and Cons of GAN Evaluation Measures: New Developments (2021, methodology): “Morozov et al. (2020) advocate for using self-supervised representations to evaluate GANs on the established non-ImageNet benchmarks 11 .”