Are Deep Neural Architectures Losing Information? Invertibility Is
Indispensable

Are Deep Neural Architectures Losing Information? Invertibility Is Indispensable

7 September 2020

Yang Liu

Saeed Anwar

Sabrina Caldwell

Tom Gedeon

Papers citing "Are Deep Neural Architectures Losing Information? Invertibility Is Indispensable"

6 / 6 papers shown

Title
Coherent Semantic Attention for Image Inpainting Hongyu Liu Bin Jiang Yi Xiao Chao Yang 60 353 0 29 May 2019
Glow: Generative Flow with Invertible 1x1 Convolutions Diederik P. Kingma Prafulla Dhariwal BDL DRL 267 3,124 0 09 Jul 2018
FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising Peng Sun W. Zuo Lei Zhang 106 2,116 0 11 Oct 2017
Faster Eigenvector Computation via Shift-and-Invert Preconditioning Dan Garber Laurent Dinh Chi Jin Jascha Narain Sohl-Dickstein Samy Bengio Praneeth Netrapalli Aaron Sidford 235 78 0 26 May 2016
Compression Artifacts Reduction by a Deep Convolutional Network Chao Dong Yubin Deng Chen Change Loy Xiaoou Tang SupR 46 793 0 27 Apr 2015
Auto-Encoding Variational Bayes Diederik P. Kingma Max Welling BDL 414 16,944 0 20 Dec 2013