Michael Tschannen

Deep Generative Models for Distribution-Preserving Lossy Compression

Oct 28, 2018
Michael Tschannen, Eirikur Agustsson, Mario Lucic

Figure 2 for Deep Generative Models for Distribution-Preserving Lossy Compression

Figure 3 for Deep Generative Models for Distribution-Preserving Lossy Compression

Figure 4 for Deep Generative Models for Distribution-Preserving Lossy Compression

* NIPS 2018. Code: https://github.com/mitscha/dplc . Changes w.r.t. v1: Some clarifications in the text and additional numerical results

Access Paper or Ask Questions

Generative Adversarial Networks for Extreme Learned Image Compression

Oct 23, 2018
Eirikur Agustsson, Michael Tschannen, Fabian Mentzer, Radu Timofte, Luc Van Gool

Figure 2 for Generative Adversarial Networks for Extreme Learned Image Compression

Figure 3 for Generative Adversarial Networks for Extreme Learned Image Compression

Figure 4 for Generative Adversarial Networks for Extreme Learned Image Compression

* EA, MT, and FM contributed equally. Project website: https://data.vision.ee.ethz.ch/aeirikur/extremecompression

Access Paper or Ask Questions

Born Again Neural Networks

Jun 29, 2018
Tommaso Furlanello, Zachary C. Lipton, Michael Tschannen, Laurent Itti, Anima Anandkumar

* Published @ICML 2018

Access Paper or Ask Questions

Noisy subspace clustering via matching pursuits

Jun 08, 2018
Michael Tschannen, Helmut Bölcskei

Figure 2 for Noisy subspace clustering via matching pursuits

Figure 3 for Noisy subspace clustering via matching pursuits

Figure 4 for Noisy subspace clustering via matching pursuits

* IEEE Transactions on Information Theory, Vol. 64, No. 6, pp. 4081-4104, June 2018
* 24 pages, 5 figures

Access Paper or Ask Questions

StrassenNets: Deep Learning with a Multiplication Budget

Jun 08, 2018
Michael Tschannen, Aran Khanna, Anima Anandkumar

Figure 2 for StrassenNets: Deep Learning with a Multiplication Budget

Figure 3 for StrassenNets: Deep Learning with a Multiplication Budget

Figure 4 for StrassenNets: Deep Learning with a Multiplication Budget

* ICML 2018. Code available at https://github.com/mitscha/strassennets

Access Paper or Ask Questions

Conditional Probability Models for Deep Image Compression

Jun 04, 2018
Fabian Mentzer, Eirikur Agustsson, Michael Tschannen, Radu Timofte, Luc Van Gool

Figure 2 for Conditional Probability Models for Deep Image Compression

Figure 3 for Conditional Probability Models for Deep Image Compression

Figure 4 for Conditional Probability Models for Deep Image Compression

* CVPR 2018. Code available at https://github.com/fab-jul/imgcomp-cvpr . The first two authors contributed equally

Access Paper or Ask Questions

Convolutional Recurrent Neural Networks for Electrocardiogram Classification

Apr 09, 2018
Martin Zihlmann, Dmytro Perekrestenko, Michael Tschannen

Figure 2 for Convolutional Recurrent Neural Networks for Electrocardiogram Classification

Figure 3 for Convolutional Recurrent Neural Networks for Electrocardiogram Classification

Figure 4 for Convolutional Recurrent Neural Networks for Electrocardiogram Classification

* 4 pages, in Computing in Cardiology (CinC) 2017, PhysioNet/CinC Challenge 2017 submission. Code available at https://github.com/yruffiner/ecg-classification

Access Paper or Ask Questions