On the Evaluation of Conditional GANs

TL;DR

This paper introduces the Frechet Joint Distance (FJD), a new single metric for evaluating conditional GANs that captures image quality, conditional consistency, and diversity simultaneously, simplifying benchmarking.

Contribution

The paper proposes the FJD metric, which unifies multiple evaluation criteria into one measure for conditional GANs, and demonstrates its effectiveness through experiments.

Findings

FJD effectively captures multiple properties in a single metric.

FJD outperforms existing metrics in benchmarking cGANs.

FJD enables consistent model comparison across diverse conditioning modalities.

Abstract

Conditional Generative Adversarial Networks (cGANs) are finding increasingly widespread use in many application domains. Despite outstanding progress, quantitative evaluation of such models often involves multiple distinct metrics to assess different desirable properties, such as image quality, conditional consistency, and intra-conditioning diversity. In this setting, model benchmarking becomes a challenge, as each metric may indicate a different "best" model. In this paper, we propose the Frechet Joint Distance (FJD), which is defined as the Frechet distance between joint distributions of images and conditioning, allowing it to implicitly capture the aforementioned properties in a single metric. We conduct proof-of-concept experiments on a controllable synthetic dataset, which consistently highlight the benefits of FJD when compared to currently established metrics. Moreover, we use the newly introduced metric to compare existing cGAN-based models for a variety of conditioning modalities (e.g. class labels, object masks, bounding boxes, images, and text captions). We show that FJD can be used as a promising single metric for cGAN benchmarking and model selection. Code can be found at https://github.com/facebookresearch/fjd.