# Twin Auxiliary Classifiers GAN

arXiv: https://arxiv.org/abs/1907.02690 · HTML: https://mlsanity.com/paper/1907.02690/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jul 2019.

## Built on by (most cited first, 8 of 8)

- [Domain Generalisation for Object Detection under Covariate and Concept Shift](https://mlsanity.com/paper/2203.05294/) (2022)
- [IB-GAN: A Unified Approach for Multivariate Time Series Classification under Class Imbalance](https://mlsanity.com/paper/2110.07460/) (2021)
- [Visual Explanations for Convolutional Neural Networks via Latent Traversal of Generative Adversarial Networks](https://mlsanity.com/paper/2111.00116/) (2021)
- [Multi-Class Multi-Instance Count Conditioned Adversarial Image Generation](https://mlsanity.com/paper/2103.16795/) (2021)
- [Mining Multi-Label Samples from Single Positive Labels](https://mlsanity.com/paper/2206.05764/) (2022)
- [Make Optimization Once and for All with Fine-grained Guidance](https://mlsanity.com/paper/2503.11462/) (2025)
- [Enhancing Stability in Training Conditional Generative Adversarial Networks via Selective Data Matching](https://mlsanity.com/paper/2107.08792/) (2021)
- [Continuous Facial Motion Deblurring](https://mlsanity.com/paper/2207.06626/) (2022)

## Abstract (arXiv)

Conditional generative models enjoy remarkable progress over the past few years. One of the popular conditional models is Auxiliary Classifier GAN (AC-GAN), which generates highly discriminative images by extending the loss function of GAN with an auxiliary classifier. However, the diversity of the generated samples by AC-GAN tends to decrease as the number of classes increases, hence limiting its power on large-scale data. In this paper, we identify the source of the low diversity issue theoretically and propose a practical solution to solve the problem. We show that the auxiliary classifier in AC-GAN imposes perfect separability, which is disadvantageous when the supports of the class distributions have significant overlap. To address the issue, we propose Twin Auxiliary Classifiers Generative Adversarial Net (TAC-GAN) that further benefits from a new player that interacts with other players (the generator and the discriminator) in GAN. Theoretically, we demonstrate that TAC-GAN can effectively minimize the divergence between the generated and real-data distributions. Extensive experimental results show that our TAC-GAN can successfully replicate the true data distributions on simulated data, and significantly improves the diversity of class-conditional image generation on real datasets.