# Dist-GAN: An Improved GAN using Distance Constraints

arXiv: https://arxiv.org/abs/1803.08887 · HTML: https://mlsanity.com/paper/1803.08887/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Mar 2018.

## Built on by (most cited first, 26 of 26)

- [Few-shot Image Generation via Cross-domain Correspondence](https://mlsanity.com/paper/2104.06820/) (2021)
- [A Closer Look at Fourier Spectrum Discrepancies for CNN-generated Images Detection](https://mlsanity.com/paper/2103.17195/) (2021)
- [Few-shot Image Generation via Adaptation-Aware Kernel Modulation](https://mlsanity.com/paper/2210.16559/) (2022)
- [Measuring Fairness in Generative Models](https://mlsanity.com/paper/2107.07754/) (2021)
- [Discovering Transferable Forensic Features for CNN-generated Images Detection](https://mlsanity.com/paper/2208.11342/) (2022)
- [Robustness via Uncertainty-aware Cycle Consistency](https://mlsanity.com/paper/2110.12467/) (2021)
- [Few-shot Image Generation with Mixup-based Distance Learning](https://mlsanity.com/paper/2111.11672/) (2021)
- [Self-Diagnosing GAN: Diagnosing Underrepresented Samples in Generative Adversarial Networks](https://mlsanity.com/paper/2102.12033/) (2021)
- [Partition-Guided GANs](https://mlsanity.com/paper/2104.00816/) (2021)
- [Exploring Semantic Consistency in Unpaired Image Translation to Generate Data for Surgical Applications](https://mlsanity.com/paper/2309.03048/) (2023)
- [EEG to fMRI Synthesis Benefits from Attentional Graphs of Electrode Relationships](https://mlsanity.com/paper/2203.03481/) (2022)
- [Dynamically Grown Generative Adversarial Networks](https://mlsanity.com/paper/2106.08505/) (2021)
- [Anomaly Detection in Additive Manufacturing Processes using Supervised Classification with Imbalanced Sensor Data based on Generative Adversarial Network](https://mlsanity.com/paper/2210.17274/) (2022)
- [DuelGAN: A Duel Between Two Discriminators Stabilizes the GAN Training](https://mlsanity.com/paper/2101.07524/) (2021)
- [Uncertainty-aware Generalized Adaptive CycleGAN](https://mlsanity.com/paper/2102.11747/) (2021)
- [CAS-GAN for Contrast-free Angiography Synthesis](https://mlsanity.com/paper/2410.08490/) (2024)
- [IID-GAN: an IID Sampling Perspective for Regularizing Mode Collapse](https://mlsanity.com/paper/2106.00563/) (2021)
- [Deep clustering with fusion autoencoder](https://mlsanity.com/paper/2201.04727/) (2022)
- [AdAM: Few-Shot Image Generation via Adaptation-Aware Kernel Modulation](https://mlsanity.com/paper/2307.01465/) (2023)
- [VENI: Variational Encoder for Natural Illumination](https://mlsanity.com/paper/2601.14079/) (2026)
- [Structure-Aware Feature Generation for Zero-Shot Learning](https://mlsanity.com/paper/2108.07032/) (2021)
- [VARGAN: Variance Enforcing Network Enhanced GAN](https://mlsanity.com/paper/2109.02117/) (2021)
- [Counting Phases and Faces Using Bayesian Thermodynamic Integration](https://mlsanity.com/paper/2206.07494/) (2022)
- [Disentangled Uncertainty and Out of Distribution Detection in Medical Generative Models](https://mlsanity.com/paper/2211.06250/) (2022)
- [Distribution Fitting for Combating Mode Collapse in Generative Adversarial Networks](https://mlsanity.com/paper/2212.01521/) (2022)
- [Representation Learning of Multivariate Time Series using Attention and Adversarial Training](https://mlsanity.com/paper/2401.01987/) (2024)

## Abstract (arXiv)

We introduce effective training algorithms for Generative Adversarial Networks (GAN) to alleviate mode collapse and gradient vanishing. In our system, we constrain the generator by an Autoencoder (AE). We propose a formulation to consider the reconstructed samples from AE as "real" samples for the discriminator. This couples the convergence of the AE with that of the discriminator, effectively slowing down the convergence of discriminator and reducing gradient vanishing. Importantly, we propose two novel distance constraints to improve the generator. First, we propose a latent-data distance constraint to enforce compatibility between the latent sample distances and the corresponding data sample distances. We use this constraint to explicitly prevent the generator from mode collapse. Second, we propose a discriminator-score distance constraint to align the distribution of the generated samples with that of the real samples through the discriminator score. We use this constraint to guide the generator to synthesize samples that resemble the real ones. Our proposed GAN using these distance constraints, namely Dist-GAN, can achieve better results than state-of-the-art methods across benchmark datasets: synthetic, MNIST, MNIST-1K, CelebA, CIFAR-10 and STL-10 datasets. Our code is published here (https://github.com/tntrung/gan) for research.