English
Related papers

Related papers: Reliable Fidelity and Diversity Metrics for Genera…

200 papers

The new wave of successful generative models in machine learning has increased the interest in deep learning driven de novo drug design. However, assessing the performance of such generative models is notoriously difficult. Metrics that are…

Machine Learning · Computer Science 2018-08-02 Kristina Preuer , Philipp Renz , Thomas Unterthiner , Sepp Hochreiter , Günter Klambauer

The rapid advancement of Generative Adversarial Networks (GANs) necessitates the need to robustly evaluate these models. Among the established evaluation criteria, the Fr\'{e}chetInception Distance (FID) has been widely adopted due to its…

Computer Vision and Pattern Recognition · Computer Science 2024-05-01 Lorenzo Luzi , Helen Jenne , Ryan Murray , Carlos Ortiz Marrero

In biomedical image analysis, data imbalance is common across several imaging modalities. Data augmentation is one of the key solutions in addressing this limitation. Generative Adversarial Networks (GANs) are increasingly being relied upon…

Image and Video Processing · Electrical Eng. & Systems 2023-08-08 Muhammad Muneeb Saad , Mubashir Husain Rehmani , Ruairi O'Reilly

Deep generative models (DGMs) of images are now sufficiently mature that they produce nearly photorealistic samples and obtain scores similar to the data distribution on heuristics such as Frechet Inception Distance (FID). These results,…

Machine Learning · Computer Science 2019-10-29 Suman Ravuri , Oriol Vinyals

Despite an impressive performance from the latest GAN for generating hyper-realistic images, GAN discriminators have difficulty evaluating the quality of an individual generated sample. This is because the task of evaluating the quality of…

Image and Video Processing · Electrical Eng. & Systems 2019-12-03 Xiru Zhu , Fengdi Che , Tianzi Yang , Tzuyang Yu , David Meger , Gregory Dudek

Modern generative models are roughly divided into two main categories: (1) models that can produce high-quality random samples, but cannot estimate the exact density of new data points and (2) those that provide exact density estimation, at…

Machine Learning · Computer Science 2022-06-24 Omri Ben-Dov , Pravir Singh Gupta , Victoria Fernandez Abrevaya , Michael J. Black , Partha Ghosh

Generative artificial intelligence (AI) models in smart grids have advanced significantly in recent years due to their ability to generate large amounts of synthetic data, which would otherwise be difficult to obtain in the real world due…

Machine Learning · Computer Science 2025-10-27 Yuting Cai , Shaohuai Liu , Chao Tian , Le Xie

Text generation is an important Natural Language Processing task with various applications. Although several metrics have already been introduced to evaluate the text generation methods, each of them has its own shortcomings. The most…

Machine Learning · Computer Science 2019-05-22 Ehsan Montahaei , Danial Alihosseini , Mahdieh Soleymani Baghshah

Achieving a balance between image quality (precision) and diversity (recall) is a significant challenge in the domain of generative models. Current state-of-the-art models primarily rely on optimizing heuristics, such as the Fr\'echet…

Machine Learning · Computer Science 2023-11-02 Alexandre Verine , Benjamin Negrevergne , Muni Sreenivas Pydi , Yann Chevaleyre

The evaluation of synthetic micro-structure images is an emerging problem as machine learning and materials science research have evolved together. Typical state of the art methods in evaluating synthetic images from generative models have…

Materials Science · Physics 2022-11-18 Devesh Shah , Anirudh Suresh , Alemayehu Admasu , Devesh Upadhyay , Kalyanmoy Deb

Recent advances in diffusion models have led to a quantum leap in the quality of generative visual content. However, quantification of realism of the content is still challenging. Existing evaluation metrics, such as Inception Score and…

Computer Vision and Pattern Recognition · Computer Science 2023-09-27 Yunzhuo Chen , Naveed Akhtar , Nur Al Hasan Haldar , Ajmal Mian

Quality and diversity have been proposed as reasonable heuristics for assessing content generated by co-creative systems, but to date there has been little agreement around what constitutes the latter or how to measure it. Proposed…

Computer Vision and Pattern Recognition · Computer Science 2024-03-22 Francisco Ibarrola , Kazjon Grace

Diffusion models have fundamentally transformed the field of generative models, making the assessment of similarity between customized model outputs and reference inputs critically important. However, traditional perceptual similarity…

Computer Vision and Pattern Recognition · Computer Science 2024-12-20 Yiren Song , Xiaokang Liu , Mike Zheng Shou

Generative models can now produce photorealistic synthetic data which is virtually indistinguishable from the real data used to train it. This is a significant evolution over previous models which could produce reasonable facsimiles of the…

Machine Learning · Computer Science 2024-12-10 Debargha Ganguly , Warren Morningstar , Andrew Yu , Vipin Chaudhary

The quality of synthetically generated images (e.g. those produced by diffusion models) are often evaluated using information about image contents encoded by pretrained auxiliary models. For example, the Fr\'{e}chet Inception Distance (FID)…

Computer Vision and Pattern Recognition · Computer Science 2025-04-07 Ciaran Bench , Spencer A. Thomas

We performed a billion locality sensitive hash comparisons between artificially generated data samples to answer the critical question - can we reproduce the results of generative AI models? Reproducibility is one of the pillars of…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-02-07 Edward Kim , Isamu Isozaki , Naomi Sirkin , Michael Robson

Image-generating machine learning models are typically trained with loss functions based on distance in the image space. This often leads to over-smoothed results. We propose a class of loss functions, which we call deep perceptual…

Machine Learning · Computer Science 2016-02-10 Alexey Dosovitskiy , Thomas Brox

Text-to-image synthesis has made encouraging progress and attracted lots of public attention recently. However, popular evaluation metrics in this area, like the Inception Score and Fr'echet Inception Distance, incur several issues. First…

Computer Vision and Pattern Recognition · Computer Science 2023-08-17 Qi Chen , Chaorui Deng , Zixiong Huang , Bowen Zhang , Mingkui Tan , Qi Wu

We show that Fr\'echet Distance (FD), long considered impractical as a training objective, can in fact be effectively optimized in the representation space. Our idea is simple: decouple the population size for FD estimation (e.g., 50k) from…

Computer Vision and Pattern Recognition · Computer Science 2026-05-01 Jiawei Yang , Zhengyang Geng , Xuan Ju , Yonglong Tian , Yue Wang

Measuring inter-dataset similarity is an important task in machine learning and data mining with various use cases and applications. Existing methods for measuring inter-dataset similarity are computationally expensive, limited, or…

Machine Learning · Computer Science 2025-05-06 Muhammad Rajabinasab , Anton D. Lautrup , Arthur Zimek