PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications

TL;DR

This paper enhances PixelCNN models by introducing a discretized logistic mixture likelihood, simplifying structure, and employing various modifications to improve training speed and performance, achieving state-of-the-art results on CIFAR-10.

Contribution

The paper presents several modifications to PixelCNN, including a new likelihood function, model simplifications, and training techniques, leading to improved efficiency and accuracy.

Findings

Achieved state-of-the-art log likelihood on CIFAR-10

Discretized logistic mixture likelihood speeds up training

Model modifications improve performance and training efficiency

Abstract

PixelCNNs are a recently proposed class of powerful generative models with tractable likelihood. Here we discuss our implementation of PixelCNNs which we make available at https://github.com/openai/pixel-cnn. Our implementation contains a number of modifications to the original model that both simplify its structure and improve its performance. 1) We use a discretized logistic mixture likelihood on the pixels, rather than a 256-way softmax, which we find to speed up training. 2) We condition on whole pixels, rather than R/G/B sub-pixels, simplifying the model structure. 3) We use downsampling to efficiently capture structure at multiple resolutions. 4) We introduce additional short-cut connections to further speed up optimization. 5) We regularize the model using dropout. Finally, we present state-of-the-art log likelihood results on CIFAR-10 to demonstrate the usefulness of these modifications.