English
Related papers

Related papers: Reliable Fidelity and Diversity Metrics for Genera…

200 papers

Despite the tremendous progress in the estimation of generative models, the development of tools for diagnosing their failures and assessing their performance has advanced at a much slower pace. Recent developments have investigated metrics…

Machine Learning · Computer Science 2020-06-09 Josip Djolonga , Mario Lucic , Marco Cuturi , Olivier Bachem , Olivier Bousquet , Sylvain Gelly

We systematically study a wide variety of generative models spanning semantically-diverse image datasets to understand and improve the feature extractors and metrics used to evaluate them. Using best practices in psychophysics, we measure…

Generative methods now produce outputs nearly indistinguishable from real data but often fail to fully capture the data distribution. Unlike quality issues, diversity limitations in generative models are hard to detect visually, requiring…

Computer Vision and Pattern Recognition · Computer Science 2024-12-13 Mischa Dombrowski , Weitong Zhang , Sarah Cechnicka , Hadrien Reynaud , Bernhard Kainz

This paper shows that two commonly used evaluation metrics for generative models, the Fr\'echet Inception Distance (FID) and the Inception Score (IS), are biased -- the expected value of the score computed for a finite sample set is not the…

Computer Vision and Pattern Recognition · Computer Science 2020-06-17 Min Jin Chong , David Forsyth

We propose a robust and reliable evaluation metric for generative models by introducing topological and statistical treatments for rigorous support estimation. Existing metrics, such as Inception Score (IS), Frechet Inception Distance…

Machine Learning · Computer Science 2024-01-25 Pum Jun Kim , Yoojin Jang , Jisu Kim , Jaejun Yoo

Assessing the fidelity and diversity of the generative model is a difficult but important issue for technological advancement. So, recent papers have introduced k-Nearest Neighbor ($k$NN) based precision-recall metrics to break down the…

Machine Learning · Computer Science 2024-01-25 Dogyun Park , Suhyun Kim

Generative models have made immense progress in recent years, particularly in their ability to generate high quality images. However, that quality has been difficult to evaluate rigorously, with evaluation dominated by heuristic approaches…

Computer Vision and Pattern Recognition · Computer Science 2019-12-30 Y. Alex Kolchinski , Sharon Zhou , Shengjia Zhao , Mitchell Gordon , Stefano Ermon

Evaluating generative models for synthetic medical imaging is crucial yet challenging, especially given the high standards of fidelity, anatomical accuracy, and safety required for clinical applications. Standard evaluation of generated…

Image and Video Processing · Electrical Eng. & Systems 2025-05-13 Yash Deo , Yan Jia , Toni Lassila , William A. P. Smith , Tom Lawton , Siyuan Kang , Alejandro F. Frangi , Ibrahim Habli

Feature embeddings acquired from pretrained models are widely used in medical applications of deep learning to assess the characteristics of datasets; e.g. to determine the quality of synthetic, generated medical images. The Fr\'{e}chet…

Machine Learning · Computer Science 2026-01-30 Ciaran Bench , Vivek Desai , Carlijn Roozemond , Ruben van Engen , Spencer A. Thomas

We introduce MEt3R, a metric for multi-view consistency in generated images. Large-scale generative models for multi-view image generation are rapidly advancing the field of 3D inference from sparse observations. However, due to the nature…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Mohammad Asim , Christopher Wewer , Thomas Wimmer , Bernt Schiele , Jan Eric Lenssen

Devising domain- and model-agnostic evaluation metrics for generative models is an important and as yet unresolved problem. Most existing metrics, which were tailored solely to the image synthesis setup, exhibit a limited capacity for…

Machine Learning · Computer Science 2022-07-14 Ahmed M. Alaa , Boris van Breugel , Evgeny Saveliev , Mihaela van der Schaar

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 field being recently…

Computer Vision and Pattern Recognition · Computer Science 2024-02-07 Ricardo de Deijn , Aishwarya Batra , Brandon Koch , Naseef Mansoor , Hema Makkena

We propose two new evaluation metrics to assess realness of generated images based on normalizing flows: a simpler and efficient flow-based likelihood distance (FLD) and a more exact dual-flow based likelihood distance (D-FLD). Because…

Computer Vision and Pattern Recognition · Computer Science 2024-10-08 Pranav Jeevan , Neeraj Nixon , Amit Sethi

Considering the difficulty of interpreting generative model output, there is significant current research focused on determining meaningful evaluation metrics. Several recent approaches utilize "precision" and "recall," borrowed from the…

Machine Learning · Computer Science 2025-02-28 Alexis Fox , Samarth Swarup , Abhijin Adiga

Generative models are typically evaluated by direct inspection of their generated samples, e.g., by visual inspection in the case of images. Further evaluation metrics like the Fr\'echet inception distance or maximum mean discrepancy are…

Information Theory · Computer Science 2024-08-02 Michael Baur , Nurettin Turan , Simon Wallner , Wolfgang Utschick

Despite remarkable progress, image generation is far from solved. The dominant metric, FID, conflates sample fidelity with mode coverage and is close to being saturated. Yet a model can still exhibit mode collapse while achieving a low FID,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Mehdi Esmaeilzadeh , Alexia Jolicoeur-Martineau , Chirag Vashist , Ke Li

Fr\'echet Inception Distance (FID) is the primary metric for ranking models in data-driven generative modeling. While remarkably successful, the metric is known to sometimes disagree with human judgement. We investigate a root cause of…

Computer Vision and Pattern Recognition · Computer Science 2023-02-15 Tuomas Kynkäänniemi , Tero Karras , Miika Aittala , Timo Aila , Jaakko Lehtinen

Evaluating image generation models such as generative adversarial networks (GANs) is a challenging problem. A common approach is to compare the distributions of the set of ground truth images and the set of generated test images. The…

Computer Vision and Pattern Recognition · Computer Science 2022-07-21 Junghyuk Lee , Jong-Seok Lee

Super-resolution results are usually measured by full-reference image quality metrics or human rating scores. However, these evaluation methods are general image quality measurement, and do not account for the nature of the super-resolution…

Computer Vision and Pattern Recognition · Computer Science 2023-03-14 Sheng Cheng

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 generative models…

Machine Learning · Computer Science 2024-06-12 Zixiao Wang , Farzan Farnia , Zhenghao Lin , Yunheng Shen , Bei Yu