论文标题
gan的实例选择
Instance Selection for GANs
论文作者
论文摘要
生成对抗网络（GAN）的最新进展导致其广泛采用，目的是产生高质量的合成图像。这些模型虽然能够生成照片真实的图像，但通常会产生不切实际的样本，这些样本落在数据歧管之外。最近提出的几种技术试图通过拒绝一代拒绝或截断模型的潜在空间来避免伪造样本。尽管有效，但这些方法效率低下，因为很大一部分培训时间和模型容量专门用于最终未使用的样品。在这项工作中，我们提出了一种新的方法来提高样本质量：在进行模型培训之前，通过实例选择更改培训数据集。通过在训练前完善经验数据分布，我们将模型的容量重定向到高密度区域，这最终改善了样本保真度，降低了模型的容量需求并大大减少了训练时间。代码可在https://github.com/uoguelph-mlrg/instance_selection_for_gans上找到。
Recent advances in Generative Adversarial Networks (GANs) have led to their widespread adoption for the purposes of generating high quality synthetic imagery. While capable of generating photo-realistic images, these models often produce unrealistic samples which fall outside of the data manifold. Several recently proposed techniques attempt to avoid spurious samples, either by rejecting them after generation, or by truncating the model's latent space. While effective, these methods are inefficient, as a large fraction of training time and model capacity are dedicated towards samples that will ultimately go unused. In this work we propose a novel approach to improve sample quality: altering the training dataset via instance selection before model training has taken place. By refining the empirical data distribution before training, we redirect model capacity towards high-density regions, which ultimately improves sample fidelity, lowers model capacity requirements, and significantly reduces training time. Code is available at https://github.com/uoguelph-mlrg/instance_selection_for_gans.
