We introduce autoregressive implicit quantile networks (AIQN), a
fundamentally different approach to generative modeling than those commonly
used, that implicitly captures the distribution using quantile regression. AIQN
is able to achieve superior perceptual quality and improvements in evaluation
metrics, without incurring a loss of sample diversity. The method can be
applied to many existing models and architectures. In this work we extend the
PixelCNN model with AIQN and demonstrate results on CIFAR-10 and ImageNet using
Inception score, FID, non-cherry-picked samples, and inpainting results. We
consistently observe that AIQN yields a highly stable algorithm that improves
perceptual quality while maintaining a highly diverse distribution.

通过引入自回归隐式分位数网络 (AIQN)，本文提出了一种与传统模型不同的生成模型方法，通过量化回归隐式地捕获分布，AIQN 可以在不损失样本多样性的情况下实现优越的感知质量和评估度量的改进，使用 Inception score、FID、非樱桃挑选样本和修补结果等指标，我们将 AIQN 扩展到 PixelCNN 模型，并在 CIFAR-10 和 ImageNet 上展示结果，结果表明，AIQN 可以稳健地提高感知质量，同时仍保持高度多样化的分布。