Follow
Michael Tschannen
Michael Tschannen
Google DeepMind
Verified email at google.com - Homepage
Title
Cited by
Cited by
Year
Born again neural networks
T Furlanello, ZC Lipton, M Tschannen, L Itti, A Anandkumar
International Conference on Machine Learning (ICML), 1602-1611, 2018
12022018
Generative adversarial networks for extreme learned image compression
E Agustsson*, M Tschannen*, F Mentzer*, R Timofte, L Van Gool
International Conference on Computer Vision (ICCV), 2019
6542019
Soft-to-hard vector quantization for end-to-end learning compressible representations
E Agustsson, F Mentzer, M Tschannen, L Cavigelli, R Timofte, L Benini, ...
Advances in Neural Information Processing Systems (NIPS), 1141-1151, 2017
6012017
Recent advances in autoencoder-based representation learning
M Tschannen, O Bachem, M Lucic
Workshop on Bayesian Deep Learning (NeurIPS 2018), 2018
5812018
On mutual information maximization for representation learning
M Tschannen*, J Djolonga*, PK Rubenstein, S Gelly, M Lucic
International Conference on Learning Representations (ICLR), 2020
5672020
Conditional probability models for deep image compression
F Mentzer, E Agustsson, M Tschannen, R Timofte, L Van Gool
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018
5612018
High-Fidelity Generative Image Compression
F Mentzer, G Toderici, M Tschannen, E Agustsson
Advances in Neural Information Processing Systems (NeurIPS), 2020
4472020
Scaling vision transformers to 22 billion parameters
M Dehghani, J Djolonga, B Mustafa, P Padlewski, J Heek, J Gilmer, ...
International Conference on Machine Learning (ICML), 7480-7512, 2023
4372023
A large-scale study of representation learning with the visual task adaptation benchmark
X Zhai, J Puigcerver, A Kolesnikov, P Ruyssen, C Riquelme, M Lucic, ...
arXiv preprint arXiv:1910.04867, 2019
421*2019
Weakly-supervised disentanglement without compromises
F Locatello, B Poole, G Rätsch, B Schölkopf, O Bachem, M Tschannen
International Conference on Machine Learning (ICML), 2020
3502020
Convolutional recurrent neural networks for electrocardiogram classification
M Zihlmann, D Perekrestenko, M Tschannen
Computing in Cardiology Conference (CinC) 44, 2017
3022017
Practical full resolution learned lossless image compression
F Mentzer, E Agustsson, M Tschannen, R Timofte, L Van Gool
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019
2282019
Disentangling factors of variation using few labels
F Locatello, M Tschannen, S Bauer, G Rätsch, B Schölkopf, O Bachem
International Conference on Learning Representations (ICLR), 2020
2012020
Towards image understanding from deep compression without decoding
R Torfason, F Mentzer, E Agustsson, M Tschannen, R Timofte, L Van Gool
International Conference on Learning Representations (ICLR), 2018
1842018
High-fidelity image generation with fewer labels
M Lucic*, M Tschannen*, M Ritter*, X Zhai, O Bachem, S Gelly
International Conference on Machine Learning (ICML), 2019
177*2019
On Robustness and Transferability of Convolutional Neural Networks
J Djolonga*, J Yung*, M Tschannen*, R Romijnders, L Beyer, ...
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021
1512021
Deep generative models for distribution-preserving lossy compression
M Tschannen, E Agustsson, M Lucic
Advances in Neural Information Processing Systems (NeurIPS), 2018
1402018
Pali-x: On scaling up a multilingual vision and language model
X Chen, J Djolonga, P Padlewski, B Mustafa, S Changpinyo, J Wu, ...
arXiv preprint arXiv:2305.18565, 2023
1372023
Heart sound classification using deep structured features
M Tschannen, T Kramer, G Marti, M Heinzmann, T Wiatowski
Computing in Cardiology Conference (CinC), 565-568, 2016
1162016
Learning Better Lossless Compression Using Lossy Compression
F Mentzer, L Van Gool, M Tschannen
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020
982020
The system can't perform the operation now. Try again later.
Articles 1–20