Lightning-AI / Lightning-AI/torchmetrics
Frechet Inception Distance with Dinov2 features
@gisilvs is already working on this.
Since Jul 4, 2025.
- Dominant language
- Python
- Stars
- 2.5k
- Forks
- 526
- Avg merge
- 6d 11h
- Merged PRs (30d)
- 5
Description
## 🚀 Feature
Implement FID computation with DinoV2 as proposed in "Exposing flaws of generative model evaluation metrics
and their unfair treatment of diffusion models"
### Motivation
Computing FID with features extraded from DinoV2 has become common practice for generative models evaluation.
### Pitch
Either add a new class `FrechetInceptionDistanceDinoV2` based on torch-fidelity's `FeatureExtractorDinoV2`.
### Alternatives
Add an option in the existing `FrechetInceptionDistance `class to choose between inveption v3 and dino v2 feature extractor, also using the `FeatureExtractorDinoV2` from torch-fidelity.
### Additional context
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Assessment
This issue has not been assessed yet.