Stochastically Flipping Labels of Discriminator’s Outputs for Training Generative Adversarial Networks
Stochastically Flipping Labels of Discriminator’s Outputs for Training Generative Adversarial Networks
复制标题
DOI：
10.1109/access.2022.3210130
复制
发表时间：
2022
期刊：
影响因子：
3.9
通讯作者：
Rui Yang;Duc Minh Vo;Hideki Nakayama
中科院分区：
文献类型：
--
作者：
Rui Yang;Duc Minh Vo;Hideki Nakayama
生成性对抗性网络(GANS)在两个神经网络之间进行对抗性博弈：生成器和鉴别器。许多研究将鉴别器的输出视为输入图像分布之前的隐式后验分布。因此，增加鉴别器的输出维度可以比增加鉴别器的单个输出维度代表更丰富的信息。然而，增加输出维度将导致一个非常强的鉴别器，它很容易超过生成器，打破对抗性学习的平衡。解决这样的冲突并提升甘斯的世代质量仍然是具有挑战性的。因此，通过扩展BipGAN中的翻转和非翻转非饱和损失，我们提出了一种基于随机选择方法的简单而有效的方法来解决这一冲突问题。我们根据著名的BigGan模型和StyleGan模型组织了实验，以进行比较。我们的实验通过几个标准的评价指标和真实世界的数据集，成功地验证了我们的方法在有限的输出维度内增强生成质量的方法，并在人脸生成任务中取得了竞争的结果。
Generative Adversarial Networks (GANs) play the adversarial game between two neural networks: the generator and the discriminator. Many studies treat the discriminator’s outputs as an implicit posterior distribution prior to the input image distribution. Thus, increasing the discriminator’s output dimensions can represent richer information than a single output dimension of the discriminator. However, increasing the output dimensions will lead to a very strong discriminator, which can easily surpass the generator and break the balance of adversarial learning. Solving such conflict and elevating the generation quality of GANs remains challenging. Hence, we propose a simple yet effective method to solve this conflict problem based on a stochastic selecting method by extending the flipped and non-flipped non-saturating losses in BipGAN. We organized our experiments based on the famous BigGAN and StyleGAN models for comparison. Our experiments successfully validated our approach to strengthening the generation quality within limited output dimensions via several standard evaluation metrics and real-world datasets and achieved competitive results in the Human face generation task.