Abstract Generative Adversarial Networks (GANs) have been widely used to generate realistic-looking instances. However, training robust GAN is a non-trivial task due to the problem of mode collapse. Although many GAN variants are proposed to overcome this problem, they have limitations. Those existing studies either generate identical instances or result in negative gradients during training. In this paper, we propose a new approach to training GAN to overcome mode collapse by employing a set of generators, an encoder and a discriminator. A new minimax formula is proposed to simultaneously train all components in a similar spirit to vanilla GAN. The orthogonal vector strategy is employed to guide multiple generators to learn different information in a complementary manner. In this way, we term our approach Multi-Generator Orthogonal GAN (MGO-GAN). Specifically, the synthetic data produced by those generators are fed into the encoder to obtain feature vectors. The orthogonal value is calculated between any two feature vectors, which loyally reflects the correlation between vectors. Such a correlation indicates how different information has been learnt by generators. The lower the orthogonal value is, the more different information the generators learn. We minimize the orthogonal value along with minimizing the generator loss through back-propagation in the training of GAN. The orthogonal value is integrated with the original generator loss to jointly update the corresponding generator’s parameters. We conduct extensive experiments utilizing MNIST, CIFAR10 and CelebA datasets to demonstrate the significant performance improvement of MGO-GAN in terms of generated data quality and diversity at different resolutions.

中文翻译：

---

使用正交向量处理多生成器 GAN 中的模式崩溃

摘要 生成对抗网络 (GAN) 已被广泛用于生成逼真的实例。然而，由于模式崩溃的问题，训练强大的 GAN 是一项重要的任务。尽管提出了许多 GAN 变体来克服这个问题，但它们都有局限性。那些现有的研究要么生成相同的实例，要么在训练期间导致负梯度。在本文中，我们提出了一种通过使用一组生成器、一个编码器和一个鉴别器来训练 GAN 以克服模式崩溃的新方法。提出了一种新的 minimax 公式，以与 vanilla GAN 类似的精神同时训练所有组件。正交向量策略用于引导多个生成器以互补的方式学习不同的信息。通过这种方式，我们将我们的方法称为多生成器正交 GAN (MGO-GAN)。具体来说，这些生成器产生的合成数据被送入编码器以获得特征向量。计算任意两个特征向量之间的正交值，忠实地反映了向量之间的相关性。这种相关性表明生成器如何学习不同的信息。正交值越低，生成器学习的不同信息就越多。我们在 GAN 的训练中通过反向传播最小化正交值并最小化生成器损失。正交值与原始生成器损失相结合，共同更新相应生成器的参数。我们利用 MNIST 进行了广泛的实验，