Talmaj Marinc
Research Subjects
Talmaj Marinc has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Arturo Marban
Department of Artificial Intelligence, Fraunhofer Heinrich Hertz Institute, Berlin, Germany
1 shared publication - Cornelius Hellge
Fraunhofer Heinrich Hertz Institute, Berlin, Germany
1 shared publication - David Neumann
Fraunhofer Heinrich Hertz Institute, Berlin, Germany
1 shared publication - Detlev Marpe
Video Communication and Applications, Fraunhofer HHI, Berlin, Germany
1 shared publication - Heiko Schwarz
Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute, Berlin, Germany
1 shared publication - Heiner Kirchhoffer
Fraunhofer Institute for Telecommunications, Heinrich-Hertz-Institute, Berlin, Germany
1 shared publication
Latest Publications
- 30 April 2020
- Published by Springer Nature
- p. 777-780
A Virtualized Video Surveillance System for Public Transportation
- 30 April 2020
- Published by Springer Nature
- p. 777-780
A Virtualized Video Surveillance System for Public Transportation
- Open Access
- 27 January 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Signal Processing
- Vol. 14 (4) , 700-714
DeepCABAC: A Universal Compression Algorithm for Deep Neural Networks
In the past decade deep neural networks (DNNs) have shown state-of-the-art performance on a wide range of complex machine learning tasks. Many of these results have been achieved while growing the size of DNNs, creating a demand for efficient compression and transmission of them. In this work we present DeepCABAC, a universal compression algorithm for DNNs that is based on applying Context-based Adaptive Binary Arithmetic Coder (CABAC) to the DNN parameters. CABAC was originally designed for the H.264/AVC video coding standard and became the state-of-the-art for the lossless compression part of video compression. DeepCABAC applies a novel quantization scheme that minimizes a rate-distortion function while simultaneously taking the impact of quantization to the DNN performance into account. Experimental results show that DeepCABAC consistently attains higher compression rates than previously proposed coding techniques for DNN compression. For instance, it is able to compress the VGG16 ImageNet model by x63.6 with no loss of accuracy, thus being able to represent the entire network with merely 9 MB. The source code for encoding and decoding can be found at https://github.com/fraunhoferhhi/DeepCABAC.
- 27 January 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Signal Processing
- Vol. 14 (4) , 700-714
Open AccessDeepCABAC: A Universal Compression Algorithm for Deep Neural Networks
In the past decade deep neural networks (DNNs) have shown state-of-the-art performance on a wide range of complex machine learning tasks. Many of these results have been achieved while growing the size of DNNs, creating a demand for efficient compression and transmission of them. In this work we present DeepCABAC, a universal compression algorithm for DNNs that is based on applying Context-based Adaptive Binary Arithmetic Coder (CABAC) to the DNN parameters. CABAC was originally designed for the H.264/AVC video coding standard and became the state-of-the-art for the lossless compression part of video compression. DeepCABAC applies a novel quantization scheme that minimizes a rate-distortion function while simultaneously taking the impact of quantization to the DNN performance into account. Experimental results show that DeepCABAC consistently attains higher compression rates than previously proposed coding techniques for DNN compression. For instance, it is able to compress the VGG16 ImageNet model by x63.6 with no loss of accuracy, thus being able to represent the entire network with merely 9 MB. The source code for encoding and decoding can be found at https://github.com/fraunhoferhhi/DeepCABAC.