论文标题
功能量化改善了GAN训练
Feature Quantization Improves GAN Training
论文作者
论文摘要
尽管进行了出色的研究工作，但GAN培训中的不稳定一直是一个长期存在的问题。我们发现，由于固定目标分布与逐渐生成的分布之间的平衡，使执行特征与迷你批量统计的特征匹配的困难引起了不稳定问题。在这项工作中，我们提出了歧视器的特征量化（FQ），将True和Fake数据样本嵌入共享离散空间中。 FQ的量化值被构造为不断发展的词典，这与最近分布历史记录的特征统计数据一致。因此，FQ隐式启用紧凑空间中的鲁棒特征匹配。我们的方法可以轻松地插入现有的GAN模型中，而培训中的计算开销很少。我们将FQ应用于9个代表性GAN模型上的9个基准：Biggan用于图像生成，式面部合成和U-Gat-IT，用于无监督的图像到图像翻译。广泛的实验结果表明，拟议的FQ-GAN可以通过各种任务来提高基线方法的FID得分，从而实现了新的最新性能。
The instability in GAN training has been a long-standing problem despite remarkable research efforts. We identify that instability issues stem from difficulties of performing feature matching with mini-batch statistics, due to a fragile balance between the fixed target distribution and the progressively generated distribution. In this work, we propose Feature Quantization (FQ) for the discriminator, to embed both true and fake data samples into a shared discrete space. The quantized values of FQ are constructed as an evolving dictionary, which is consistent with feature statistics of the recent distribution history. Hence, FQ implicitly enables robust feature matching in a compact space. Our method can be easily plugged into existing GAN models, with little computational overhead in training. We apply FQ to 3 representative GAN models on 9 benchmarks: BigGAN for image generation, StyleGAN for face synthesis, and U-GAT-IT for unsupervised image-to-image translation. Extensive experimental results show that the proposed FQ-GAN can improve the FID scores of baseline methods by a large margin on a variety of tasks, achieving new state-of-the-art performance.
