skip to content
Home

Department of Applied Mathematics and Theoretical Physics

Dr Christian Etmann

I am a Postdoc at the Cambridge Image Analysis group. My research interests include

  • deep learning
  • inverse problems
  • invertible neural networks
  • medical imaging (in particular high-dimensional 3D data)
  • adversarial examples

Publications

Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans
M Roberts, D Driggs, M Thorpe, J Gilbey, M Yeung, S Ursprung, AI Aviles-Rivero, C Etmann, C McCague, L Beer, JR Weir-McCall, Z Teng, E Gkrania-Klotsas, A Ruggiero, A Korhonen, E Jefferson, E Ako, G Langs, G Gozaliasl, G Yang, H Prosch, J Preller, J Stanczuk, J Tang, J Hofmanninger, J Babar, LE Sánchez, M Thillai, PM Gonzalez, P Teare, X Zhu, M Patel, C Cafolla, H Azadbakht, J Jacob, J Lowe, K Zhang, K Bradley, M Wassin, M Holzer, K Ji, MD Ortet, T Ai, N Walton, P Lio, S Stranks, T Shadbahr, W Lin, Y Zha, Z Niu, JHF Rudd, E Sala, CB Schönlieb
– Nature Machine Intelligence
(2021)
3,
199
(DOI: 10.1038/s42256-021-00307-0)
iUNets: Learnable Invertible Up- and Downsampling for Large-Scale Inverse Problems
C Etmann, R Ke, CB Schonlieb
– IEEE International Workshop on Machine Learning for Signal Processing, MLSP
(2020)
2020-September,
1
(DOI: 10.1109/mlsp49062.2020.9231874)
On the connection between adversarial robustness and saliency map interpretability
C Etmann, S Lunz, P Maass, CB Schönlieb
– 36th International Conference on Machine Learning, ICML 2019
(2019)
2019-June,
3255
Structure preserving deep learning
E Celledoni, MJ Ehrhardt, C Etmann, RI McLachlan, B Owren, C-B Schönlieb, F Sherry
Equivariant neural networks for inverse problems
E Celledoni, MJ Ehrhardt, C Etmann, B Owren, C-B Schönlieb, F Sherry
Wasserstein GANs Work Because They Fail (to Approximate the Wasserstein Distance)
J Stanczuk, C Etmann, LM Kreusser, C-B Schönlieb

Research Group

Cambridge Image Analysis

Room

F2.05

Study at Cambridge

About the University

Research at Cambridge