Michael Tschannen Dr. sc. ETH Zurich, MSc ETH EE & IT

Additional Information

This page is no longer maintained. Please see my new website.

Code: See individual papers in the list below and Github.

Google Scholar profile

Note: Michael Tschannen is no longer with our group.

Publications

• Journal Papers and Manuscripts
  • Noisy subspace clustering via matching pursuits
    M. Tschannen and H. Bölcskei, IEEE Transactions on Information Theory, Vol. 64, No. 6, pp. 4081-4104, June 2018.
  • Robust nonparametric nearest neighbor random process clustering
    M. Tschannen and H. Bölcskei, IEEE Transactions on Signal Processing, Vol. 65, No. 22, pp. 6009-6023, Nov. 2017.
  • Dimensionality-reduced subspace clustering
    R. Heckel, M. Tschannen, and H. Bölcskei, Information and Inference: A Journal of the IMA, Vol. 6, No. 3, pp. 246-283, Sept. 2017.
  • Regression forest-based automatic estimation of the articular margin plane for shoulder prosthesis planning
    M. Tschannen, L. Vlachopoulos, C. Gerber, G. Székely, and P. Fürnstahl, Medical Image Analysis, Vol. 31, pp. 88-97, July 2016.

• Conference, Symposium, and Workshop Papers
  • High-fidelity image generation with fewer labels
    M. Lucic, M. Tschannen, M. Ritter, X. Zhai, O. Bachem, and S. Gelly, prerint, 2019, submitted.
  • Practical full resolution learned lossless image compression
    F. Mentzer, E. Agustsson, M. Tschannen, R. Timofte, and L. Van Gool, Proc. of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, to appear.
  • Deep generative models for distribution-preserving lossy compression
    M. Tschannen, E. Agustsson, and M. Lucic, Neural Information Processing Systems (NeurIPS), 2018, to appear.
  • Generative adversarial networks for extreme learned image compression
    E. Agustsson, M. Tschannen, F. Mentzer, R. Timofte, and L. Van Gool, preprint, 2018, submitted.
  • Recent advances in autoencoder-based representation learning
    M. Tschannen, O. Bachem, and M. Lucic, Third workshop on Bayesian Deep Learning (NeurIPS 2018), 2018.
  • Born again neural networks
    T. Furlanello, Z. C. Lipton, M. Tschannen, L. Itti, and A. Anandkumar, Proc. of International Conference on Machine Learning (ICML), pp. 1602–1611, July 2018.
  • StrassenNets: Deep learning with a multiplication budget
    M. Tschannen, A. Khanna, and A. Anandkumar, Proc. of International Conference on Machine Learning (ICML), pp. 4992–5001, July 2018.
  • Conditional probability models for deep image compression
    F. Mentzer, E. Agustsson, M. Tschannen, R. Timofte, and L. Van Gool, Proc. of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4394–4402, June 2018.
  • Towards image understanding from deep compression without decoding
    R. Torfason, F. Mentzer, E. Agustsson, M. Tschannen, R. Timofte, and L. Van Gool, International Conference on Learning Representations (ICLR), Apr. 2018.
  • Greedy algorithms for cone constrained optimization with convergence guarantees
    F. Locatello, M. Tschannen, G. Rätsch, and M. Jaggi, Neural Information Processing Systems (NIPS), pp. 773-784, Dec. 2017.
  • Soft-to-hard vector quantization for end-to-end learning compressible representations
    E. Agustsson, F. Mentzer, M. Tschannen, L. Cavigelli, R. Timofte, L. Benini, and L. Van Gool, Neural Information Processing Systems (NIPS), pp. 1141-1151, Dec. 2017.
  • Convolutional recurrent neural networks for electrocardiogram classification
    M. Zihlmann, D. Perekrestenko, and M. Tschannen, 2017 Computing in Cardiology (CinC), Rennes, France, pp. 1-4, Sept. 2017.
  • Deep structured features for semantic segmentation
    M. Tschannen, L. Cavigelli, F. Mentzer, T. Wiatowski, and L. Benini, Proc. of European Signal Processing Conference (EUSIPCO), pp. 61-65, Sept. 2017.
  • A unified optimization view on generalized matching pursuit and Frank-Wolfe
    F. Locatello, R. Khanna, M. Tschannen, and M. Jaggi, Proc. of International Conference on Artificial Intelligence and Statistics (AISTATS), pp. 860-868, Feb. 2017.
  • Heart sound classification using deep structured features
    M. Tschannen, T. Kramer, G. Marti, M. Heinzmann, and T. Wiatowski, Computing in Cardiology (CinC), Vancouver, Canada, pp. 565-568, Sept. 2016.
  • Discrete deep feature extraction: A theory and new architectures
    T. Wiatowski, M. Tschannen, A. Stanić, P. Grohs, and H. Bölcskei, Proc. of International Conference on Machine Learning (ICML), New York, USA, pp. 2149-2158, June 2016.
  • Nonparametric nearest neighbor random process clustering
    M. Tschannen and H. Bölcskei, Proc. of IEEE International Symposium on Information Theory (ISIT), Hong Kong, China, pp. 1207-1211, June 2015.
  • Subspace clustering of dimensionality-reduced data
    R. Heckel, M. Tschannen, and H. Bölcskei, Proc. of IEEE International Symposium on Information Theory (ISIT), Honolulu, HI, pp. 2997-3001, July 2014.
  • A learning-based approach for fast and robust vessel tracking in long ultrasound sequences
    V. De Luca, M. Tschannen, G. Székely, and C. Tanner, Proc. of International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), pp. 518-525, Sept. 2013.

Supervised Theses

• Diploma Theses
  • Torfason, Robert, "Towards Image Understanding from Deep Compression without Decoding," Spring semester 2017
    Supervisor(s): Eirikur Agustsson, Michael Tschannen
  • Mentzer, Fabian, "End-to-End Learned Image Compression Using Deep Neural Networks," Fall semester 2016
    Supervisor(s): Eirikur Agustsson, Michael Tschannen, Lukas Cavigelli
  • Thandiackal, Kevin, "Wavelet-Based Convolutional Neural Networks for Reinforcement Learning," Spring semester 2016
    Supervisor(s): Michael Tschannen, Thomas Wiatowski
  • Dünner, Celestine, "Performance Analysis of Spectral Clustering with Application to Subspace Clustering," Fall semester 2014
    Supervisor(s): Michael Tschannen, Reinhard Heckel

• Student Projects
  • Yardim, Ali Batuhan, "Learned Priors for Variational Autoencoders," Spring semester 2019
    Supervisor(s): Michael Tschannen
  • Kaya, Berk, "Representation Learning and Speech Compression Using Distribution-Preserving Lossy Compression," Fall semester 2018
    Supervisor(s): Michael Tschannen
  • Montazeri, Kristófer, "Efficient Neural Networks for Keyword Spotting," Spring semester 2018
    Supervisor(s): Michael Tschannen, Dmytro Perekrestenko
  • Donhauser, Konstantin, "Learning Ensembles of Neural Networks in Function Space," Spring semester 2018
    Supervisor(s): Michael Tschannen
  • Ruffiner, Yannick, "Convolutional Recurrent Neural Networks for Electrocardiogram Classification," Fall semester 2017
    Supervisor(s): Dmytro Perekrestenko, Michael Tschannen
  • Laumer, Fabian, "Convolutional Recurrent Neural Networks for Heart Sound Segmentation," Spring semester 2017
    Supervisor(s): Michael Tschannen, Dmytro Perekrestenko
  • Zihlmann, Martin, "A Convolutional Recurrent Neural Network for Atrial Fibrillation Detection in Single Lead ECGs," Spring semester 2017
    Supervisor(s): Michael Tschannen, Dmytro Perekrestenko
  • Jetzer, Sarah, "Scene Labeling Using Deep Structured Features," Spring semester 2017
    Supervisor(s): Lukas Cavigelli, Michael Tschannen
  • Vandroux, Lucas, "Recommender System Based on Aesthetic Preference Models," Fall semester 2016
    Supervisor(s): Michael Tschannen
  • Mentzer, Fabian, "Scene Labeling Using Deep Structured Features," Spring semester 2016
    Supervisor(s): Michael Tschannen, Lukas Cavigelli, Thomas Wiatowski, Michael Lerjen
  • Kühne, Jonas, "Scattering Networks for Scene Labeling," Fall semester 2015
    Supervisor(s): Michael Tschannen, Lukas Cavigelli, Thomas Wiatowski, Michael Lerjen
  • Vultier, Fabien, "Hardware Design Tradeoffs for Subspace Clustering Algorithms," Fall semester 2015
    Supervisor(s): Michael Tschannen, Michael Lerjen
  • Geiger, Christian, "Feature Importance of Scattering Coefficients in Facial Landmark Detection," Fall semester 2015
    Supervisor(s): Michael Tschannen, Thomas Wiatowski
  • Scheidegger, Florian, "Hardware Design Tradeoffs for Subspace Clustering Algorithms," Spring semester 2015
    Supervisor(s): Michael Tschannen, Michael Lerjen

• Group Projects
  • Heinzmann, Matthias; Kramer, Thomas; Marti, Gian, "A Python Implementation for Deep Structured Feature Extraction," Spring semester 2016
    Supervisor(s): Thomas Wiatowski, Michael Tschannen