# Twin Auxiliary Classifiers GAN Source: [Twin Auxiliary Classifiers GAN]() Collection index: [llms.txt]() Data updated: 2026-01-04T03:07:12.443Z Authors: Mingming Gong, Yanwu Xu, Chunyuan Li, Kun Zhang, Kayhan Batmanghelich Published: 2019-07-05T06:29:06.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Class-conditional image generation on VGGFace200](): Class-conditional Image Generation; VGGFace200; IS: 109.04. - [Class-conditional image generation on VGGFace500](): Class-conditional Image Generation; VGGFace500; Inception Score: 77.76. - [Class-conditional image generation on VGGFace1000](): Class-conditional Image Generation; VGGFace1000; IS: 108.89. - [Class-conditional image generation on CIFAR100](): Class-conditional Image Generation; CIFAR100; Inception Score: 9.34. - [Class-conditional image generation on ImageNet 1000](): Class-conditional Image Generation; ImageNet-1000; IS: 28.86. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()