Timezone: »

 
Talk
Parallel Multiscale Autoregressive Density Estimation
Scott Reed · Aäron van den Oord · Nal Kalchbrenner · Sergio Gómez Colmenarejo · Ziyu Wang · Yutian Chen · Dan Belov · Nando de Freitas

Sun Aug 06 05:48 PM -- 06:06 PM (PDT) @ Parkside 1

PixelCNN achieves state-of-the-art results in density estimation for natural images. Although training is fast, inference is costly, requiring one network evaluation per pixel; O(N) for N pixels. This can be sped up by caching activations, but still involves generating each pixel sequentially. In this work, we propose a parallelized PixelCNN that allows more efficient inference by modeling certain pixel groups as conditionally independent. Our new PixelCNN model achieves competitive density estimation and orders of magnitude speedup - O(log N) sampling instead of O(N) - enabling the practical generation of 512x512 images. We evaluate the model on class-conditional image generation, text-to-image synthesis, and action-conditional video generation, showing that our model achieves the best results among non-pixel-autoregressive density models that allow efficient sampling.

Author Information

Scott Reed (Google Deepmind)
Aäron van den Oord (Google)
Nal Kalchbrenner (DeepMind)
Sergio Gómez Colmenarejo (Google DeepMind)
Ziyu Wang (Deep Mind)
Yutian Chen (DeepMind)
Dan Belov (Google)
Nando de Freitas (DeepMind)

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

More from the Same Authors