benchmarks
critique
bearish
FID and KID cannot distinguish between under-dispersion (mode collapse) and over-dispersion because they are symmetric scalar discrepancies
FID and KID are scalar discrepancies that are unchanged when the two samples are exchanged and therefore do not encode the direction of a dispersion change: under-dispersion, as can occur in mode collapse, versus over-dispersion
Machine Learning (Statistics)29 Aug 2026