AI RESEARCH
Rethinking FID Through the Geometry of the Reference Dataset
arXiv CS.AI
•
ArXi:2605.29335v1 Announce Type: cross Fr\'echet Inception Distance (FID) is widely used to evaluate image generators, yet lower FID does not always correspond to better sample quality. We show that this mismatch depends in part on the geometry of the reference dataset. In a controlled study across six datasets, distributional density and effective rank significantly explain how FID changes as sample quality improves. Concentrated datasets tend to yield favorable FID trends, whereas dispersed datasets can make FID worsen despite better samples.