# On the Evaluation of Conditional GANs

arXiv: https://arxiv.org/abs/1907.08175 · HTML: https://mlsanity.com/paper/1907.08175/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jul 2019.

## Built on by (most cited first, 21 of 21)

- [Large Scale Image Completion via Co-Modulated Generative Adversarial Networks](https://mlsanity.com/paper/2103.10428/) (2021)
- [Adversarial Text-to-Image Synthesis: A Review](https://mlsanity.com/paper/2101.09983/) (2021)
- [Time Weaver: A Conditional Time Series Generation Model](https://mlsanity.com/paper/2403.02682/) (2024)
- [Conditional Frechet Inception Distance](https://mlsanity.com/paper/2103.11521/) (2021)
- [Novel View Synthesis with Pixel-Space Diffusion Models](https://mlsanity.com/paper/2411.07765/) (2024)
- [Data synthesis and adversarial networks: A review and meta-analysis in cancer imaging](https://mlsanity.com/paper/2107.09543/) (2021)
- [Scendi Score: Prompt-Aware Diversity Evaluation via Schur Complement of CLIP Embeddings](https://mlsanity.com/paper/2412.18645/) (2024)
- [Distilling and Transferring Knowledge via cGAN-generated Samples for Image Classification and Regression](https://mlsanity.com/paper/2104.03164/) (2021)
- [DIG In: Evaluating Disparities in Image Generations with Indicators for Geographic Diversity](https://mlsanity.com/paper/2308.06198/) (2023)
- [The Intricate Dance of Prompt Complexity, Quality, Diversity, and Consistency in T2I Models](https://mlsanity.com/paper/2510.19557/) (2025)
- [Efficient Subsampling of Realistic Images From GANs Conditional on a Class or a Continuous Variable](https://mlsanity.com/paper/2103.11166/) (2021)
- [Explainable Artificial Intelligence Methods in Combating Pandemics: A Systematic Review](https://mlsanity.com/paper/2112.12705/) (2021)
- [Automated Performance Testing Based on Active Deep Learning](https://mlsanity.com/paper/2104.02102/) (2021)
- [Appreciate the View: A Task-Aware Evaluation Framework for Novel View Synthesis](https://mlsanity.com/paper/2511.12675/) (2025)
- [Generating Photo-realistic Images from LiDAR Point Clouds with Generative Adversarial Networks](https://mlsanity.com/paper/2112.11245/) (2021)
- [Art Creation with Multi-Conditional StyleGANs](https://mlsanity.com/paper/2202.11777/) (2022)
- [Generative Models with Information-Theoretic Protection Against Membership Inference Attacks](https://mlsanity.com/paper/2206.00071/) (2022)
- [MCGAN: Enhancing GAN Training with Regression-Based Generator Loss](https://mlsanity.com/paper/2405.17191/) (2024)
- [Generating Multi-type Temporal Sequences to Mitigate Class-imbalanced Problem](https://mlsanity.com/paper/2104.03428/) (2021)
- [Generating Clear Images From Images With Distortions Caused by Adverse Weather Using Generative Adversarial Networks](https://mlsanity.com/paper/2211.05234/) (2022)
- [MID: Mask-Image Distributional Divergence for Evaluating Medical Image Segmentation](https://mlsanity.com/paper/2610.17354/) (2026)

## Abstract (arXiv)

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.