# DeepCABAC: Context-adaptive binary arithmetic coding for deep neural network compression

Source: [DeepCABAC: Context-adaptive binary arithmetic coding for deep neural network compression](<https://www.sota2.com/research/paper/68fa55db1e209131ce997a60>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T13:49:44.067Z

Authors: Simon Wiedemann, Heiner Kirchhoffer, Stefan Matlage, Paul Haase, Arturo Marban, Talmaj Marinc, David Neumann, Ahmed Osman, Detlev Marpe, Heiko Schwarz, Thomas Wiegand, Wojciech Samek

Published: 2019-05-15T13:36:27.000Z

## Abstract

We present DeepCABAC, a novel context-adaptive binary arithmetic coder for compressing deep neural networks. It quantizes each weight parameter by minimizing a weighted rate-distortion function, which implicitly takes the impact of quantization on to the accuracy of the network into account. Subsequently, it compresses the quantized values into a bitstream representation with minimal redundancies. We show that DeepCABAC is able to reach very high compression ratios across a wide set of different network architectures and datasets. For instance, we are able to compress by x63.6 the VGG16 ImageNet model with no loss of accuracy, thus being able to represent the entire network with merely 8.7MB.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1905.08318>)

[PDF](<https://arxiv.org/pdf/1905.08318.pdf>)