Timezone: »

Autoregressive Quantile Networks for Generative Modeling
Georg Ostrovski · Will Dabney · Remi Munos

Fri Jul 13 07:20 AM -- 07:40 AM (PDT) @ A7

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 scores, 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.

Author Information

Georg Ostrovski (DeepMind)
Will Dabney (DeepMind)
Remi Munos (DeepMind)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors