.png){kind=icon}
.png){kind=icon}
Return
Deep dive into generative models through feature interpoint distances
.png){kind=icon}
PRE
AI
DOI：10.1016/j.jocs.2025.102539.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This paper introduces the Interpoint Inception Distance (IID) as a new approach for evaluating deep generative models. It is based on reducing the measurement of discrepancy between multidimensional feature distributions to one-dimensional interpoint comparisons. Our method provides a general tool for deriving a wide range of evaluation measures. The Cram & eacute;r Interpoint Inception Distance (CIID) is notable for its theoretical properties, including a Gaussian-free structure of feature distribution and a strongly consistent estimator. Our experiments, conducted on both synthetic and large-scale real or generated data, suggest that CIID is a promising competitor to the Fr & eacute;chet Inception Distance (FID), which is currently the primary metric for evaluating deep generative models. This article is an extended version of the ICCS 2024 conference paper (Jaje & sacute;niak et al., 2024) [1].
Keywords:
Deep generative model
Evaluation metric
Fr & eacute
chet Inception Distance (FID)
Feature Likelihood Divergence (FLD)
Cram & eacute
r Distance
Journal
IF:
18.3
Papers:
3.1K
Citations:
4.0K