most citedAccelerating Training of Deep Neural Networks with a Standardization Loss

2 citations · 2 across the 1 of their papers we have counts for

collaborators

6 papers

cs.LG2019

Scalable Model Compression by Entropy Penalized Reparameterization

Deniz Oktay, Johannes Ballé, Saurabh Singh +1

We describe a simple and general neural network weight compression approach, in which the network parameters (weights and biases) are represented in a "latent" space, amounting to…

cs.LG20192 cited

Accelerating Training of Deep Neural Networks with a Standardization Loss

Jasmine Collins, Johannes Balle, Jonathon Shlens

A significant advance in accelerating neural network training has been the development of normalization methods, permitting the training of deep models both faster and with better…

cs.CV2018

Joint Autoregressive and Hierarchical Priors for Learned Image Compression

David Minnen, Johannes Ballé, George Toderici

Recent models for learned image compression are based on autoencoders, learning approximately invertible mappings from pixels to a quantized latent representation. These are combin…

cs.CV2018

Towards a Semantic Perceptual Image Metric

Troy Chinen, Johannes Ballé, Chunhui Gu +8

We present a full reference, perceptual image metric based on VGG-16, an artificial neural network trained on object classification. We fit the metric to a new database based on 14…

eess.IV2018

Variational image compression with a scale hyperprior

Johannes Ballé, David Minnen, Saurabh Singh +2

We describe an end-to-end trainable model for image compression based on variational autoencoders. The model incorporates a hyperprior to effectively capture spatial dependencies i…

eess.IV2018

Efficient Nonlinear Transforms for Lossy Image Compression

Johannes Ballé

We assess the performance of two techniques in the context of nonlinear transform coding with artificial neural networks, Sadam and GDN. Both techniques have been successfully used…