# Dual Discriminator Generative Adversarial Nets

arXiv: https://arxiv.org/abs/1709.03831 · HTML: https://mlsanity.com/paper/1709.03831/

## Key facts

- Cited by 55 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Sep 2017.

## Built on by (most cited first, 30 of 55)

- [Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection](https://mlsanity.com/paper/2203.16220/) (2022)
- [A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT](https://mlsanity.com/paper/2303.04226/) (2023)
- [Free Lunch for Domain Adversarial Training: Environment Label Smoothing](https://mlsanity.com/paper/2302.00194/) (2023)
- [Convolutional Transformer based Dual Discriminator Generative Adversarial Networks for Video Anomaly Detection](https://mlsanity.com/paper/2107.13720/) (2021)
- [Synthetic data, real errors: how (not) to publish and use synthetic data](https://mlsanity.com/paper/2305.09235/) (2023)
- [Fair Generative Models via Transfer Learning](https://mlsanity.com/paper/2212.00926/) (2022)
- [Cross-View Panorama Image Synthesis](https://mlsanity.com/paper/2203.11832/) (2022)
- [How Do Flow Matching Models Memorize and Generalize in Sample Data Subspaces?](https://mlsanity.com/paper/2410.23594/) (2024)
- [Improving Multimodal fusion via Mutual Dependency Maximisation](https://mlsanity.com/paper/2109.00922/) (2021)
- [Applications of Generative Adversarial Networks in Anomaly Detection: A Systematic Literature Review](https://mlsanity.com/paper/2110.12076/) (2021)
- [MCL-GAN: Generative Adversarial Networks with Multiple Specialized Discriminators](https://mlsanity.com/paper/2107.07260/) (2021)
- [Partition-Guided GANs](https://mlsanity.com/paper/2104.00816/) (2021)
- [Dual Discriminator Adversarial Distillation for Data-free Model Compression](https://mlsanity.com/paper/2104.05382/) (2021)
- [Self-Supervised GANs with Label Augmentation](https://mlsanity.com/paper/2106.08601/) (2021)
- [MIND: Inductive Mutual Information Estimation, A Convex Maximum-Entropy Copula Approach](https://mlsanity.com/paper/2102.13182/) (2021)
- [Game of GANs: Game-Theoretical Models for Generative Adversarial Networks](https://mlsanity.com/paper/2106.06976/) (2021)
- [Dynamically Grown Generative Adversarial Networks](https://mlsanity.com/paper/2106.08505/) (2021)
- [Robust Imitation via Mirror Descent Inverse Reinforcement Learning](https://mlsanity.com/paper/2210.11201/) (2022)
- [Adversarial Information Bottleneck](https://mlsanity.com/paper/2103.00381/) (2021)
- [DuelGAN: A Duel Between Two Discriminators Stabilizes the GAN Training](https://mlsanity.com/paper/2101.07524/) (2021)
- [Structured Latent Embeddings for Recognizing Unseen Classes in Unseen Domains](https://mlsanity.com/paper/2107.05622/) (2021)
- [Generative Adversarial Networks and Adversarial Autoencoders: Tutorial and Survey](https://mlsanity.com/paper/2111.13282/) (2021)
- [Facial Expression Translation using Landmark Guided GANs](https://mlsanity.com/paper/2209.02136/) (2022)
- [Signal Propagation in a Gradient-Based and Evolutionary Learning System](https://mlsanity.com/paper/2102.08929/) (2021)
- [Overcoming Mode Collapse with Adaptive Multi Adversarial Training](https://mlsanity.com/paper/2112.14406/) (2021)
- [Unsupervised Clustering of Roman Potsherds via Variational Autoencoders](https://mlsanity.com/paper/2203.07437/) (2022)
- [PReGAN: Answer Oriented Passage Ranking with Weakly Supervised GAN](https://mlsanity.com/paper/2207.01762/) (2022)
- [Learning From Positive and Unlabeled Data Using Observer-GAN](https://mlsanity.com/paper/2208.12477/) (2022)
- [MAAIP: Multi-Agent Adversarial Interaction Priors for imitation from fighting demonstrations for physics-based characters](https://mlsanity.com/paper/2311.02502/) (2023)
- [G3FA: Geometry-guided GAN for Face Animation](https://mlsanity.com/paper/2408.13049/) (2024)

## Abstract (arXiv)

We propose in this paper a novel approach to tackle the problem of mode collapse encountered in generative adversarial network (GAN). Our idea is intuitive but proven to be very effective, especially in addressing some key limitations of GAN. In essence, it combines the Kullback-Leibler (KL) and reverse KL divergences into a unified objective function, thus it exploits the complementary statistical properties from these divergences to effectively diversify the estimated density in capturing multi-modes. We term our method dual discriminator generative adversarial nets (D2GAN) which, unlike GAN, has two discriminators; and together with a generator, it also has the analogy of a minimax game, wherein a discriminator rewards high scores for samples from data distribution whilst another discriminator, conversely, favoring data from the generator, and the generator produces data to fool both two discriminators. We develop theoretical analysis to show that, given the maximal discriminators, optimizing the generator of D2GAN reduces to minimizing both KL and reverse KL divergences between data distribution and the distribution induced from the data generated by the generator, hence effectively avoiding the mode collapsing problem. We conduct extensive experiments on synthetic and real-world large-scale datasets (MNIST, CIFAR-10, STL-10, ImageNet), where we have made our best effort to compare our D2GAN with the latest state-of-the-art GAN's variants in comprehensive qualitative and quantitative evaluations. The experimental results demonstrate the competitive and superior performance of our approach in generating good quality and diverse samples over baselines, and the capability of our method to scale up to ImageNet database.