Contact Information

CRIStAL UMR CNRS 9189

Email

john DOT klein AT univ-lille.fr

Address

Université de Lille, Bureau 205, P2 Building, avenue Carl Gauss 59655 Villeneuve d'Acsq, France.

Position

Senior Research Scientist, (Associate Prof. on leave)

On leave at Owkin !!

Short Bio

Since September 2009, I am a (tenured) associate professor at the University of Lille (formerly University of Lille1 Sciences and Technologies). I belong to the faculty of sciences and technologies which is located in the “Cité Scientifique” campus of Villeneuve d’Ascq. I am a member of the department of electrical engineering and automation department but I also teach in the department of computer sciences. I am also affiliated to CRIStAL, the research center in computer sciences, automatic control and signal processing of the university.

I obtained the H.D.R. in computer sciences from the University of Lille in 2017 and a Ph.D. in information sciences from the University of Rouen in 2008. Prior to that, I was an intern in Beijing University and I obtained a Master degree from the University of Bordeaux1 and ENSEIRB.

Research

Topic: Data sciences and Artificial Intelligence

• AI - Reasoning : I have a strong interest in the information fusion paradigm and more generally in artificial reasoning under uncertainty frameworks allowing to perform fusion. Among these formalisms, I developed several contributions in the field of belief functions. These functions are spanned by probabilistic mechanisms when events can be assigned three epistemic states (true, false or unknown). Thanks to this generalization, belief functions are a model that better fits many situations or data in which several forms of uncertainty are involved. Click here to learn more on belief functions.

• AI - Learning : I also have interests in machine learning and especially in ensembling and aggregation methods which share some ideas with information fusion. More recently, I have also been working on deep learning applied to image processing tasks such as segmentation, style transfer or secure secret message embedding (steganography). Finally, I am also interested in state-space models such as particle filtering / sequential Monte Carlo.

Publications

Journal papers

A. Deleruyelle, J. Klein, C. Versari. Self-mentoring: A new deep learning pipeline to train a self-supervised U-net for few-shot learning of bio-artificial capsule segmentation, in Computers in Biology and Medicine, vol. 152, pp. 106454, 2023. doi: 10.1016/j.compbiomed.2022.106454 - PDF

S. Bernard, P. Bas, J. Klein, T. Pevný, Backpack: a Backpropagable Adversarial Embedding Scheme, in IEEE Transactions on Information Forensics and Security, vol. 17, pp. 3539 - 3554, 2022, https://doi.org/10.1109/TIFS.2022.3204218 - PDF

R. Min, C. Garnier, F. Septier, J. Klein. State space partitioning based on constrained spectral clustering for block particle filtering, in Signal Processing, vol. 201, pp. 108727, 2022, https://doi.org/10.1016/j.sigpro.2022.108727 - PDF

K. Brou Boni, J. Klein , A. Gulyban, D. Pasquier and N. Reynaert, Improving generalization in MR to CT synthesis in radiotherapy using an augmented cycle generative adversarial network with unpaired data, in Medical Physics, vol. 48(6), pp. 3003-3010, 2021, https://doi.org/10.1002/mp.14866 CODE - PDF

S. Bernard, P. Bas, J. Klein, T. Pevný, Explicit Optimization of min max Steganographic Game, in IEEE Transactions on Information Forensics and Security, vol.16, pp. 818–823, 2020, https://dx.doi.org/10.1109/TIFS.2020.3021913 - PDF

K. Brou Boni, J. Klein , L. Vanquin, A. Wagner, T. Lacornerie, D. Pasquier and N. Reynaert, MR to CT synthesis with multicenter data in the pelvic era using a conditional generative adversarial network, in Physics in Medicine and Biology, vol. 65(7), p.075002, 2020, https://doi.org/10.1088/1361-6560/ab7633 - PDF

J. Klein, M. Albardan, O. Colot, SPOCC: Scalable POssibilistic Classifier Combination – toward robust aggregation of classifiers, in Expert Systems With Applications, vol.150, 113332, 2020, https://doi.org/10.1016/j.eswa.2020.113332 - PDF - CODE

J. Klein, Complementary Lipschitz continuity results for the distribution of intersections or unions of independent random sets in finite discrete spaces, in International Journal of Approximate Reasoning, vol. 110, pp. 164-184, 2019, https://doi.org/10.1016/j.ijar.2019.04.007 - PDF

S. Destercke, F. Pichon, J. Klein From set relations to belief function relations, in International Journal of Approximate Reasoning, vol. 110, pp. 46-63, 2019, https://doi.org/10.1016/j.ijar.2019.04.002 - PDF

A. Desreveaux, A. Bouscayrol, R. Trigui, E. Castex, J. Klein Impact of the Velocity Profile on Energy Consumption of Electric Vehicles, in IEEE Transactions on Vehicular Technology, vol. 68, no. 12, pp. 11420-11426, 2019, https://doi.org/10.1109/TVT.2019.2949215

J. Klein, S. Destercke, O. Colot, Idempotent conjunctive and disjunctive combination of belief functions by distance minimization, in International Journal of Approximate Reasoning, vol. 92, pp. 32-48, 2018, https://doi.org/10.1016/j.ijar.2017.10.004 - Code - PDF

J. Klein, S. Destercke, O. Colot, Interpreting evidential distances by connecting them to partial orders: Application to belief function approximation, in International Journal of Approximate Reasoning, vol. 71, pp. 15-33, April 2016, http://dx.doi.org/ 10.1016/j.ijar.2016.01.001. - PDF

S. Li, H. Wang, Y. Tian, A. Aitouche and J. Klein. Direct power control of DFIG wind turbine systems based on an intelligent proportional-integral sliding mode control, in ISA Transactions, vol. 64, pp. 431-439, September 2016, http://dx.doi.org/10.1016/j.isatra.2016.06.003. - PDF

M. Loudahi, J. Klein, J. M. Vannobel and O. Colot, Evidential Matrix Metrics as Distances Between Meta-Data Dependent Bodies of Evidence, in IEEE Transactions on Cybernetics, vol. 46, no. 1, pp. 109-122, Jan. 2016., doi: 10.1109/TCYB.2015.2395877 - PDF

M. Loudahi, J. Klein, J.-M. Vannobel, O. Colot, New distances between bodies of evidence based on Dempsterian specialization matrices and their consistency with the conjunctive combination rule, in International Journal of Approximate Reasoning, vol. 55, issue 5, pp. 1093-1112, July 2014, http://dx.doi.org/10.1016/j.ijar.2014.02.007. - PDF

C. Feudjio, J. Klein, A. Tiedeu, O. Colot, Automatic extraction of pectoral muscle in the MLO view of mammograms, in Physics in Medicine and Biology, vol.58 , no. 23, pp.8493-515, 2013, doi: 10.1088/0031-9155/58/23/8493. - PDF

J. Klein and O. Colot, Singular sources mining using evidential conflict analysis in International Journal of Approximate Reasoning, vol. 52, pp. 1433–1451, Dec. 2011, http://dx.doi.org/10.1016/j.ijar.2011.08.005 - PDF

J. Klein, C. Lecomte and P. Miché, Hierarchical and conditional combination of belief functions induced by visual tracking, in International Journal of Approximate Reasoning, vol. 51, pp. 410-428, March 2010, http://dx.doi.org/10.1016/j.ijar.2009.12.001 - PDF

Conference papers

E. Levecqye, J. Klein, P. Bas, J. Butora, Toward Reliable JPEG Steganalysis (at QF100), in IEEE International Workshop on Information Forensics and Security (WIFS), Shanghai, China, 2022. PDF

A. Deleruyelle, J. Klein, C. Versari. SODA: Self-organizing data augmentation in deep neural networks - Application to biomedical image segmentation tasks, in IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Singapore, 2022. doi: 10.1109/ICASSP43922.2022.9747744 - PDF

R. Min, C. Garnier, F. Septier, J. Klein. Parallel Block Particle Filtering, in IEEE Statistical Signal Processing Workshop, SSP 2021, pp. 86-90, Rio de Janeiro, Brazil, 2021. doi: 10.1109/SSP49050.2021.9513788

S. Bernard, P. Bas, J. Klein, T. Pevný, Optimizing Additive Approximations of Non-Additive Distortion Functions, in ACM workshop on Information Hiding and Multimedia Security, IH&MMSec’21, pp. 105-112, Brussels, Belgium, 2021. doi: 10.1145/3437880.3460407 PDF - Best student paper award

R. Min, C. Garnier, F. Septier, J. Klein. Block Kalman Filter: an asymptotic block particle tilter in the linear Gaussian case, in IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2021, pp. 5574-5578, Toronto, Canada, 2021. doi: 10.1109/ICASSP39728.2021.9413963

J. Klein, M. Albardan, B. Guedj, O. Colot. Decentralized learning with budgeted network load using Gaussian copulas and classifier ensembles, in Cellier P., Driessens K. (eds) Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2019, Communications in Computer and Information Science, vol 1167, Würzburg, Germany, September 16th, 2020. doi: 10.1007/978-3-030-43823-4_26 PDF - CODE

S. Bernard, T. Pevný, P. Bas, J. Klein. Exploiting Adversarial Embeddings for Better Steganography, in ACM workshop on Information Hiding and Multimedia Security, IH&MMSec’19, Paris, France, July 3-5, 2019. doi: 10.1145/3335203.3335737 - PDF - Best student paper award

S. Destercke, F. Pichon, J. Klein. From relations between sets to relations between belief functions, in Belief Functions: Theory and Applications: Fifth International Conference, BELIEF 2018, Compiègne, France, September 17-21, 2018. Lecture Notes in Computer Science, Springer. doi: 10.1007/978-3-319-99383-6_9 - PDF

J. Klein, S. Destercke, O. Colot. Idempotent Conjunctive Combination of Belief Functions by Distance Minimization, in Belief Functions: Theory and Applications: Fourth International Conference, BELIEF 2016, Prague, Czech Republic, September 21-23, 2016. Lecture Notes in Computer Science, Springer. doi: 10.1007/978-3-319-45559-4_16 Best paper award - PDF - CODE

J. Klein, M. Loudahi, J. M. Vannobel, O. Colot, α-Junctions of Categorical Mass Functions, in Belief Functions: Theory and Applications: Third International Conference, BELIEF 2014, Oxford, UK, September 26-28, 2014. Lecture Notes in Artificial Intelligence, Springer, doi: 10.1007/978-3-319-11191-9_1 - PDF

M. Loudahi, J. Klein, J. M. Vannobel, O. Colot, Fast Computation of Lp Norm-Based Specialization Distances between Bodies of Evidence, in Belief Functions: Theory and Applications: Third International Conference, BELIEF 2014, Oxford, UK, September 26-28, 2014. Lecture Notes in Artificial Intelligence, Springer, doi: 10.1007/978-3-319-11191-9_46 - PDF

J. Klein, O. Colot, A Belief Function Model for Pixel Data, in Belief Functions: Theory and Applications: Second International Conference, BELIEF 2012, Compiègne, France, September 26-28, 2014. Lecture Notes in Artificial Intelligence, Springer, doi: 10.1007/978-3-642-29461-7_22 - PDF

J. Klein, O. Colot, Automatic discounting rate computation using a dissent criterion, in Belief Functions: Theory and Applications: First International Conference, BELIEF 2010, Brest, France, September 26-28, 2010. - PDF

J. Klein, C. Lecomte and P. Miché, Preceding car tracking using belief functions and a particle filter, in IEEE International Conference on Pattern Recognition, ICPR 2008, Tampa, FL, USA, December 8-11, 2008, doi:10.1109/ICPR.2008.4761008 - PDF

J. Klein, C. Lecomte and P. Miché, Tracking objects in videos with texture features, in IEEE International Conference on Electronics, Circuits and Systems, ICECS 2007, Marrakech, Morocco, December 11-14, 2007, doi:10.1109/ICECS.2007.4511049 - PDF

J. Klein, C. Lecomte and P. Miché, Fast Color-Texture Discrimination: Application to Car Tracking, in IEEE Intelligent Transportation Systems Conference, ITSC 2007, Seattle, WA, USA, September 30- October 3, 2007, doi:10.1109/ITSC.2007.4357765 - PDF

Abstracts

K. Brou Boni, L. Vanquin, A. Wagner, D. Pasquier, J. Klein and N. Reynaert, High-Resolution Synthetic-CT Generation with Conditional Generative Adversarial Networks, in Magnetic Resonance in Radio-Therapy, MRinRT 2019,Toronto, Canada, July 2019.

Thesis

J. Klein, Algebraic and metric structures for belief functions, HDR thesis, defended on December the 7th, 2017. Université Lille1 Sciences et Technologies. - SLIDES - PDF

J. Klein, Suivi robuste d’objets dans les séquences d’images par fusion de sources, application au suivi de véhicules dans des scènes routières, PhD thesis (in French), defended on December the 4th, 2008. Université de Rouen. - PDF

Technical Reports

J. Klein, Machine learning perspectives for smart buildings: an overview, technical report for the INCASE project, October 2017, Université de Lille1 Sciences et Technologies. - PDF

Teaching

I am passionate with teaching and deeply involved in each unit I participate in. I systematically renew teaching contents (both lectures and practicals) when I take over a unit. I also update these contents every year based on students’ feedback and colleagues’ suggestions.

Here is the list of my current activities

• Machine Learning > unit details (in French).
• Real Time Operating Systems > unit details (in French).
• Ensemble Learning > unit details (in English).
• Signal Processing > unit details (in French).
• Mobile Robotics > unit details (in French).
• UML > unit details (in French).
• Software Engineering > unit details (in French).

In the past, I also taught linear control, digital electronics as well as C, C++ and Java programming.

Responsibility

I led the automation teaching team between 2012 and 2019. This team has 12 tenured members, 4 non teaching staff members and from 2 to 6 temporary members. We are responsible for teaching units dealing with computer engineering, automatic control and signal processing in the faculty of sciences of technologies. We teach every year to around 500 students.

Copyright © John Klein 2017