论文标题
冻结鉴别器：简单的基线用于微调gan
Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANs
论文作者
论文摘要
生成的对抗网络（GAN）在计算机视觉，图形和机器学习方面表现出出色的性能，但通常需要大量的培训数据和大量的计算资源。为了解决此问题，几种方法在GAN培训中引入了转移学习技术。但是，他们要么容易过度拟合，要么仅限于学习小型分配变化。在本文中，我们表明，与歧视器的冷冻层冷冻层的简单微调表现出色。这种简单的基线，冻结，显着优于以前在无条件和条件gan中使用的先前技术。我们在几个动物脸，动漫脸，牛津花，200-2011和Caltech-256数据集上使用Stylegan和Sngan-Procottion架构表现出一致的效果。代码和结果可在https://github.com/sangwoomo/freezed上找到。
Generative adversarial networks (GANs) have shown outstanding performance on a wide range of problems in computer vision, graphics, and machine learning, but often require numerous training data and heavy computational resources. To tackle this issue, several methods introduce a transfer learning technique in GAN training. They, however, are either prone to overfitting or limited to learning small distribution shifts. In this paper, we show that simple fine-tuning of GANs with frozen lower layers of the discriminator performs surprisingly well. This simple baseline, FreezeD, significantly outperforms previous techniques used in both unconditional and conditional GANs. We demonstrate the consistent effect using StyleGAN and SNGAN-projection architectures on several datasets of Animal Face, Anime Face, Oxford Flower, CUB-200-2011, and Caltech-256 datasets. The code and results are available at https://github.com/sangwoomo/FreezeD.
