Search Results for author: Johannes Ballé

Found 21 papers, 7 papers with code

Do Neural Networks Compress Manifolds Optimally?

no code implementations17 May 2022 Sourbh Bhadane, Aaron B. Wagner, Johannes Ballé

Artificial Neural-Network-based (ANN-based) lossy compressors have recently obtained striking results on several sources.

Optimizing the Communication-Accuracy Trade-off in Federated Learning with Rate-Distortion Theory

1 code implementation7 Jan 2022 Nicole Mitchell, Johannes Ballé, Zachary Charles, Jakub Konečný

A significant bottleneck in federated learning (FL) is the network communication cost of sending model updates from client devices to the central server.

Federated Learning Quantization

Neural Video Compression using GANs for Detail Synthesis and Propagation

no code implementations26 Jul 2021 Fabian Mentzer, Eirikur Agustsson, Johannes Ballé, David Minnen, Nick Johnston, George Toderici

Our approach significantly outperforms previous neural and non-neural video compression methods in a user study, setting a new state-of-the-art in visual quality for neural methods.

Video Compression

On the relation between statistical learning and perceptual distances

no code implementations ICLR 2022 Alexander Hepburn, Valero Laparra, Raul Santos-Rodriguez, Johannes Ballé, Jesús Malo

Since machine learning relies on the statistics of training data as well, the above connection has interesting implications when using perceptual distances (which mimic the behavior of the human visual system) as a loss function.

BIG-bench Machine Learning Perceptual Distance

3D Scene Compression through Entropy Penalized Neural Representation Functions

no code implementations26 Apr 2021 Thomas Bird, Johannes Ballé, Saurabh Singh, Philip A. Chou

We unify these steps by directly compressing an implicit representation of the scene, a function that maps spatial coordinates to a radiance vector field, which can then be queried to render arbitrary viewpoints.

End-to-end Learning of Compressible Features

1 code implementation23 Jul 2020 Saurabh Singh, Sami Abu-El-Haija, Nick Johnston, Johannes Ballé, Abhinav Shrivastava, George Toderici

We propose a learned method that jointly optimizes for compressibility along with the task objective for learning the features.


An Unsupervised Information-Theoretic Perceptual Quality Metric

no code implementations NeurIPS 2020 Sangnie Bhardwaj, Ian Fischer, Johannes Ballé, Troy Chinen

We show that PIM is competitive with supervised metrics on the recent and challenging BAPPS image quality assessment dataset and outperforms them in predicting the ranking of image compression methods in CLIC 2020.

Image Compression Image Quality Assessment +2

Computationally Efficient Neural Image Compression

no code implementations18 Dec 2019 Nick Johnston, Elad Eban, Ariel Gordon, Johannes Ballé

Image compression using neural networks have reached or exceeded non-neural methods (such as JPEG, WebP, BPG).

Image Compression

Scalable Model Compression by Entropy Penalized Reparameterization

no code implementations ICLR 2020 Deniz Oktay, Johannes Ballé, Saurabh Singh, Abhinav Shrivastava

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 a reparameterization.

General Classification Model Compression

Joint Autoregressive and Hierarchical Priors for Learned Image Compression

3 code implementations NeurIPS 2018 David Minnen, Johannes Ballé, George Toderici

While it is well known that autoregressive models come with a significant computational penalty, we find that in terms of compression performance, autoregressive and hierarchical priors are complementary and, together, exploit the probabilistic structure in the latents better than all previous learned models.

Image Compression MS-SSIM +1

Towards a Semantic Perceptual Image Metric

no code implementations1 Aug 2018 Troy Chinen, Johannes Ballé, Chunhui Gu, Sung Jin Hwang, Sergey Ioffe, Nick Johnston, Thomas Leung, David Minnen, Sean O'Malley, Charles Rosenberg, George Toderici

We present a full reference, perceptual image metric based on VGG-16, an artificial neural network trained on object classification.

Image Quality Assessment

Efficient Nonlinear Transforms for Lossy Image Compression

3 code implementations31 Jan 2018 Johannes Ballé

We assess the performance of two techniques in the context of nonlinear transform coding with artificial neural networks, Sadam and GDN.

Image Compression

Eigen-Distortions of Hierarchical Representations

no code implementations NeurIPS 2017 Alexander Berardino, Johannes Ballé, Valero Laparra, Eero P. Simoncelli

We develop a method for comparing hierarchical image representations in terms of their ability to explain perceptual sensitivity in humans.

Object Recognition

Perceptually Optimized Image Rendering

no code implementations23 Jan 2017 Valero Laparra, Alex Berardino, Johannes Ballé, Eero P. Simoncelli

We develop a framework for rendering photographic images, taking into account display limitations, so as to optimize perceptual similarity between the rendered image and the original scene.

End-to-end Optimized Image Compression

13 code implementations5 Nov 2016 Johannes Ballé, Valero Laparra, Eero P. Simoncelli

We describe an image compression method, consisting of a nonlinear analysis transformation, a uniform quantizer, and a nonlinear synthesis transformation.

Image Compression MS-SSIM +1

End-to-end optimization of nonlinear transform codes for perceptual quality

no code implementations18 Jul 2016 Johannes Ballé, Valero Laparra, Eero P. Simoncelli

We introduce a general framework for end-to-end optimization of the rate--distortion performance of nonlinear transform codes assuming scalar quantization.


Density Modeling of Images using a Generalized Normalization Transformation

1 code implementation19 Nov 2015 Johannes Ballé, Valero Laparra, Eero P. Simoncelli

The data are linearly transformed, and each component is then normalized by a pooled activity measure, computed by exponentiating a weighted sum of rectified and exponentiated components and a constant.

A model of sensory neural responses in the presence of unknown modulatory inputs

no code implementations6 Jul 2015 Neil C. Rabinowitz, Robbe L. T. Goris, Johannes Ballé, Eero P. Simoncelli

Neural responses are highly variable, and some portion of this variability arises from fluctuations in modulatory factors that alter their gain, such as adaptation, attention, arousal, expected or actual reward, emotion, and local metabolic resource availability.

The local low-dimensionality of natural images

no code implementations20 Dec 2014 Olivier J. Hénaff, Johannes Ballé, Neil C. Rabinowitz, Eero P. Simoncelli

We develop a new statistical model for photographic images, in which the local responses of a bank of linear filters are described as jointly Gaussian, with zero mean and a covariance that varies slowly over spatial position.


Cannot find the paper you are looking for? You can Submit a new open access paper.