PixelSNAIL: An Improved Autoregressive Generative Model

ICML 2018 Xi ChenNikhil MishraMostafa RohaninejadPieter Abbeel

Autoregressive generative models consistently achieve the best results in density estimation tasks involving high dimensional data, such as images or audio. They pose density estimation as a sequence modeling task, where a recurrent neural network (RNN) models the conditional distribution over the next element conditioned on all previous elements... (read more)

PDF Abstract

Results from the Paper


#2 best model for Image Generation on CIFAR-10 (NLL Test metric)

     Get a GitHub badge
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK LEADERBOARD
Image Generation CIFAR-10 PixelSNAIL NLL Test 2.85 # 2