E
Emily Denton
Researcher at Google
Publications - 51
Citations - 9280
Emily Denton is an academic researcher from Google. The author has contributed to research in topics: Computer science & Accountability. The author has an hindex of 24, co-authored 46 publications receiving 6027 citations. Previous affiliations of Emily Denton include Structural Genomics Consortium & Facebook.
Papers
More filters
Proceedings Article
Deep generative image models using a Laplacian pyramid of adversarial networks
TL;DR: A generative parametric model capable of producing high quality samples of natural images using a cascade of convolutional networks within a Laplacian pyramid framework to generate images in a coarse-to-fine fashion.
Proceedings Article
Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
TL;DR: In this paper, the authors exploit the redundancy present within the convolutional filters to derive approximations that significantly reduce the required computation, while keeping the accuracy within 1% of the original model.
Proceedings ArticleDOI
Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding
Chitwan Saharia,V. K. Chan,Saurabh Saxena,Lala Li,Jay Whang,Emily Denton,Seyed Kamyar Seyed Ghasemipour,Burcu Karagol Ayan,Seyedeh Sara Mahdavi,Raphael Gontijo Lopes,Tim Salimans,Jonathan Ho,David J. Fleet,Mahmood Norouzi +13 more
TL;DR: This work presents Imagen, a text-to-image diffusion model with an unprecedented degree of photorealism and a deep level of language understanding, and finds that human raters prefer Imagen over other models in side-by-side comparisons, both in terms of sample quality and image-text alignment.
Posted Content
Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
TL;DR: In this article, a Laplacian pyramid of GANs is used to generate images in a coarse-to-fine fashion, where a separate GAN model is trained at each level of the pyramid.
Posted Content
Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
TL;DR: Using large state-of-the-art models, this work demonstrates speedups of convolutional layers on both CPU and GPU by a factor of 2 x, while keeping the accuracy within 1% of the original model.