paper-with-me

Papers

MIND: Monge Inception Distance for Generative Models Evaluation

2026-05-07 · Quentin Berthet, Yu-Han Wu, Clement Crepy, Romuald Elie, Klaus Greff, Michael Eli Sander arxiv

We propose the Monge Inception Distance (MIND), a metric for evaluating generative models that addresses key limitations of the widely adopted Fréchet Inception Distance (FID). The MIND metric leverages the sliced Wasserstein distance to compare distributions by averaging one-dimensional optimal transport distances, efficiently computed via sorting. This approach circumvents the estimation of high-dimensional means and covariance matrices, which underlie FID's poor sample complexity and vulnerability to adversarial attacks. We empirically demonstrate three primary advantages: (i) it is more sample-efficient by one order of magnitude, (ii) it is faster to compute by two orders of magnitude, (iii) it is more robust to adversarial attacks such as moment-matching. We show that MIND with 5k samples can replace the evaluation performance of FID with 50k samples, providing high correlation with this standard benchmark and superior discriminative performance. We further demonstrate that even smaller sample sizes (e.g., 1k or 2k) remain highly informative for rapid model iteration.

📄 PDF Abstract BibTeX arXiv:2605.06797

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

LOB-ID: Evaluating Synthetic Market Data by Inception Distances

2026-08-13 · Andreea Bacalum, Zhuohan Wang, Ollie Olby, Martin Garaj 외 arxiv

Generative models of limit orderbook (LOB) data have advanced rapidly, but their evaluation often focuses on stylised facts and selected market statistics. These measures provide useful diagnostics but may not capture th…

A Pragmatic Note on Evaluating Generative Models with Fréchet Inception Distance for Retinal Image Synthesis

2025-02-24 · Yuli Wu, Fucheng Liu, Rüveyda Yilmaz, Henning Konermann 외

Fr\'echet Inception Distance (FID), computed with an ImageNet pretrained Inception-v3 network, is widely used as a state-of-the-art evaluation metric for generative models. It assumes that feature vectors from Inception-…

Image Generation

On the Distributed Evaluation of Generative Models

2023-10-18 · Zixiao Wang, Farzan Farnia, Zhenghao Lin, Yunheng Shen 외

The evaluation of deep generative models has been extensively studied in the centralized setting, where the reference data are drawn from a single probability distribution. On the other hand, several applications of gene…

AvgFederated Learning

Reviewing FID and SID Metrics on Generative Adversarial Networks

2024-02-06 · Ricardo de Deijn, Aishwarya Batra, Brandon Koch, Naseef Mansoor 외

The growth of generative adversarial network (GAN) models has increased the ability of image processing and provides numerous industries with the technology to produce realistic image transformations. However, with the f…

Generative Adversarial Network

Backpropagating through Fréchet Inception Distance

2020-09-29 · Alexander Mathiasen, Frederik Hvilshøj

The Fr\'echet Inception Distance (FID) has been used to evaluate hundreds of generative models. We introduce FastFID, which can efficiently train generative models with FID as a loss function. Using FID as an additional …