On the Evaluation of Conditional GANs
This addresses the problem of inconsistent benchmarking for researchers and practitioners using cGANs, though it is incremental as it builds on existing evaluation methods.
The paper tackles the challenge of evaluating conditional GANs by proposing the Frechet Joint Distance (FJD), a single metric that captures image quality, conditional consistency, and diversity, and demonstrates its benefits in proof-of-concept experiments and comparisons across various conditioning modalities.
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.