论文标题
修复噪声：用于转移式学习的删除源功能
Fix the Noise: Disentangling Source Feature for Transfer Learning of StyleGAN
论文作者
论文摘要
TyleGan的转移学习最近显示出解决各种任务的巨大潜力，尤其是在域翻译中。以前的方法通过在传输学习过程中交换或冻结权重来利用源模型，但是，它们对视觉质量和控制源特征有限制。换句话说，他们需要其他计算要求的模型，并且具有限制控制步骤，以防止平稳过渡。在本文中，我们提出了一种克服这些局限性的新方法。我们没有交换或冻结，而是引入了一个简单的功能匹配损失，以提高发电质量。此外，为了控制源特征的程度，我们使用拟议的策略FixNoise训练目标模型，以保留目标特征空间的分离子空间中的源特征。由于分离的特征空间，我们的方法可以平稳地控制单个模型中的源特征的程度。广泛的实验表明，所提出的方法比以前的工作可以产生更一致和逼真的图像。
Transfer learning of StyleGAN has recently shown great potential to solve diverse tasks, especially in domain translation. Previous methods utilized a source model by swapping or freezing weights during transfer learning, however, they have limitations on visual quality and controlling source features. In other words, they require additional models that are computationally demanding and have restricted control steps that prevent a smooth transition. In this paper, we propose a new approach to overcome these limitations. Instead of swapping or freezing, we introduce a simple feature matching loss to improve generation quality. In addition, to control the degree of source features, we train a target model with the proposed strategy, FixNoise, to preserve the source features only in a disentangled subspace of a target feature space. Owing to the disentangled feature space, our method can smoothly control the degree of the source features in a single model. Extensive experiments demonstrate that the proposed method can generate more consistent and realistic images than previous works.
