Publications

2022

• A variant of Young’s method in voting theory providing the same winners as Copeland’s method
  
  • Hudry Olivier
  International Journal of Mathematics, Statistics and Operations Research, Academic Research Foundations, 2022, 1 (2), pp.101-107.
• Generalized Fast Multichannel Nonnegative Matrix Factorization Based on Gaussian Scale Mixtures for Blind Source Separation
  
  • Fontaine Mathieu
  • Sekiguchi Kouhei
  • Nugraha Aditya
  • Bando Yoshiaki
  • Yoshii Kazuyoshi
  IEEE/ACM Transactions on Audio, Speech and Language Processing, Institute of Electrical and Electronics Engineers, 2022, pp.1-1. This paper describes heavy-tailed extensions of a state-of-the-art versatile blind source separation method called fast multichannel nonnegative matrix factorization (FastMNMF) from a unified point of view. The common way of deriving such an extension is to replace the multivariate complex Gaussian distribution in the likelihood function with its heavy-tailed generalization, e.g., the multivariate complex Student's t and leptokurtic generalized Gaussian distributions, and tailor-make the corresponding parameter optimization algorithm. Using a wider class of heavy-tailed distributions called a Gaussian scale mixture (GSM), i.e., a mixture of Gaussian distributions whose variances are perturbed by positive random scalars called impulse variables, we propose GSM-FastMNMF and develop an expectationmaximization algorithm that works even when the probability density function of the impulse variables have no analytical expressions. We show that existing heavy-tailed FastMNMF extensions are instances of GSM-FastMNMF and derive a new instance based on the generalized hyperbolic distribution that include the normal-inverse Gaussian, Student's t, and Gaussian distributions as the special cases. Our experiments show that the normalinverse Gaussian FastMNMF outperforms the state-of-the-art FastMNMF extensions and ILRMA model in speech enhancement and separation in terms of the signal-to-distortion ratio. (10.1109/TASLP.2022.3172631)
  DOI : 10.1109/TASLP.2022.3172631
• La fève du boulanger
  
  • Zayana Karim
  • Michalak Pierre
  • Bréheret Richard
  • Boyer Ivan
  CultureMath, ENS, 2022.
• Some Rainbow Problems in Graphs Have Complexity Equivalent to Satisfiability Problems
  
  • Hudry Olivier
  • Lobstein Antoine
  International Transactions in Operational Research, Wiley, 2022, 29 (3), pp.1547-1572. In a vertex-coloured graph, a set of vertices S is said to be a rainbow set if every colour in the graph appears exactly once in S. We investigate the complexities of various problems dealing with domination in vertex-coloured graphs (existence of rainbow dominating sets, of rainbow locating-dominating sets, of rainbow identifying sets), including when we ask for a unique solution: we show equivalence between these complexities and those of the well-studied Boolean satisfiability problems. (10.1111/itor.12847)
  DOI : 10.1111/itor.12847
• Real-time Virtual-Try-On from a Single Example Image through Deep Inverse Graphics and Learned Differentiable Renderers
  
  • Kips Robin
  • Jiang Ruowei
  • Ba Sileye
  • Duke Brendan
  • Perrot Matthieu
  • Gori Pietro
  • Bloch Isabelle
  Computer Graphics Forum, Wiley, 2022. Augmented reality applications have rapidly spread across online platforms, allowing consumers to virtually try-on a variety of products, such as makeup, hair dying, or shoes. However, parametrizing a renderer to synthesize realistic images of a given product remains a challenging task that requires expert knowledge. While recent work has introduced neural rendering methods for virtual try-on from example images, current approaches are based on large generative models that cannot be used in real-time on mobile devices. This calls for a hybrid method that combines the advantages of computer graphics and neural rendering approaches. In this paper we propose a novel framework based on deep learning to build a real-time inverse graphics encoder that learns to map a single example image into the parameter space of a given augmented reality rendering engine. Our method leverages self-supervised learning and does not require labeled training data which makes it extendable to many virtual try-on applications. Furthermore, most augmented reality renderers are not differentiable in practice due to algorithmic choices or implementation constraints to reach real-time on portable devices. To relax the need for a graphics-based differentiable renderer in inverse graphics problems, we introduce a trainable imitator module. Our imitator is a generative network that learns to accurately reproduce the behavior of a given non-differentiable renderer. We propose a novel rendering sensitivity loss to train the imitator, which ensures that the network learns an accurate and continuous representation for each rendering parameter. Our framework enables novel applications where consumers can virtually try-on a novel unknown product from an inspirational reference image on social media. It can also be used by graphics artists to automatically create realistic rendering from a reference product image.
• Multiple instance learning on deep features for weakly supervised object detection with extreme domain shifts
  
  • Gonthier Nicolas
  • Ladjal Saïd
  • Gousseau Yann
  Computer Vision and Image Understanding, Elsevier, 2022, 214. Weakly supervised object detection (WSOD) using only image-level annotations has attracted a growing attention over the past few years. Whereas such task is typically addressed with a domain-specific solution focused on natural images, we show that a simple multiple instance approach applied on pre-trained deep features yields excellent performances on non-photographic datasets, possibly including new classes. The approach does not include any fine-tuning or cross-domain learning and is therefore efficient and possibly applicable to arbitrary datasets and classes. We investigate several flavors of the proposed approach, some including multi-layers perceptron and polyhedral classifiers. Despite its simplicity, our method shows competitive results on a range of publicly available datasets, including paintings (People-Art, IconArt), watercolors, cliparts and comics and allows to quickly learn unseen visual categories. (10.1016/j.cviu.2021.103299)
  DOI : 10.1016/j.cviu.2021.103299
• Statistical learning from biased training samples
  
  • Clémençon Stéphan
  • Laforgue Pierre
  Electronic Journal of Statistics, Shaker Heights, OH : Institute of Mathematical Statistics, 2022, 16 (2), pp.6086-6134. With the deluge of digitized information in the Big Data era, massive datasets are becoming increasingly available for learning predictive models. However, in many practical situations, the poor control of the data acquisition processes may naturally jeopardize the outputs of machine learning algorithms, and selection bias issues are now the subject of much attention in the literature. The present article investigates how to extend Empirical Risk Minimization, the principal paradigm in statistical learning, when training observations are generated from biased models, i.e., from distributions that are different from that in the test/prediction stage, and absolutely continuous with respect to the latter. Precisely, we show how to build a “nearly debiased” training statistical population from biased samples and the related biasing functions, following in the footsteps of the approach originally proposed in [46]. Furthermore, we study from a nonasymptotic perspective the performance of minimizers of an empirical version of the risk computed from the statistical population thus created. Remarkably, the learning rate achieved by this procedure is of the same order as that attained in absence of selection bias. Beyond the theoretical guarantees, we also present experimental results supporting the relevance of the algorithmic approach promoted in this paper. (10.1214/22-EJS2084)
  DOI : 10.1214/22-EJS2084
• Cybersecurity in Smart Homes: Architectures, Solutions and Technologies
  
  • Khatoun Rida
  , 2022. Smart homes use Internet-connected devices, artificial intelligence, protocols and numerous technologies to enable people to remotely monitor their home, as well as manage various systems within it via the Internet using a smartphone or a computer. A smart home is programmed to act autonomously to improve comfort levels, save energy and potentially ensure safety; the result is a better way of life. Innovative solutions continue to be developed by researchers and engineers and thus smart home technologies are constantly evolving. By the same token, cybercrime is also becoming more prevalent. Indeed, a smart home system is made up of connected devices that cybercriminals can infiltrate to access private information, commit cyber vandalism or infect devices using botnets. This book addresses cyber attacks such as sniffing, port scanning, address spoofing, session hijacking, ransomware and denial of service. It presents, analyzes and discusses the various aspects of cybersecurity as well as solutions proposed by the research community to counter the risks. Cybersecurity in Smart Homes is intended for people who wish to understand the architectures, protocols and different technologies used in smart homes.
• Towards Globally Optimized Hybrid Homomorphic Encryption - Featuring the Elisabeth Stream Cipher
  
  • Cosseron Orel
  • Hoffmann Clément
  • Méaux Pierrick
  • Standaert François-Xavier
  , 2022.
• Participation de l’équipe TGV à DEFT 2022 : Prédiction automatique de notes d’étudiants à des questionnaires en fonction du type de question
  
  • Gaudray Bouju Vanessa
  • Guettier Margot
  • Lerus Gwennola
  • Guibon Gaël
  • Labeau Matthieu
  • Lefeuvre Luce
  , 2022, pp.23-35. Cet article présente l’approche de l’équipe TGV lors de sa participation à la tâche de base de DEFT 2022, dont l’objectif était de prédire automatiquement les notes obtenues par des étudiants sur la base de leurs réponses à des questionnaires. Notre stratégie s’est focalisée sur la mise au point d’une méthode de classification des questions en fonction du type de réponse qu’elles attendent, de manière à pouvoir mener une approche différenciée pour chaque type. Nos trois runs ont consisté en une approche non différenciée, servant de référence, et deux approches différenciées, la première se basant sur la constitution d’un jeu de caractéristiques et la seconde sur le calcul de TF-IDF et de la fonction de hashage. Notre objectif premier était ainsi de vérifier si des approches dédiées à chaque type de questions sont préférables à une approche globale.
• Characterization of the majority matrices of profiles of equivalence relations
  
  • Hudry Olivier
  , 2022.
• PBRE: A Rule Extraction Method from Trained Neural Networks Designed for Smart Home Services
  
  • Qiu Mingming
  • Najm Elie
  • Sharrock Rémi
  • Traverson Bruno
  , 2022, 13427, pp.158-173. Designing smart home services is a complex task when multiple services with a large number of sensors and actuators are deployed simultaneously. It may rely on knowledge-based or data-driven approaches. The former can use rule-based methods to design services statically, and the latter can use learning methods to discover inhabitants’ preferences dynamically. However, neither of these approaches is entirely satisfactory because rules cannot cover all possible situations that may change, and learning methods may make decisions that are sometimes incomprehensible to the inhabitant. In this paper, PBRE (Pedagogic Based Rule Extractor) is proposed to extract rules from learning methods to realize dynamic rule generation for smart home systems. The expected advantage is that both the explainability of rule-based methods and the dynamicity of learning methods are adopted. We compare PBRE with an existing rule extraction method, and the results show better performance of PBRE. We also apply PBRE to extract rules from a smart home service represented by an NRL (Neural Network-based Reinforcement Learning). The results show that PBRE can help the NRL-simulated service to make understandable suggestions to the inhabitant. (10.1007/978-3-031-12426-6_13)
  DOI : 10.1007/978-3-031-12426-6_13
• DNN-FREE LOW-LATENCY ADAPTIVE SPEECH ENHANCEMENT BASED ON FRAME-ONLINE BEAMFORMING POWERED BY BLOCK-ONLINE FASTMNMF
  
  • Nugraha Aditya Arie
  • Sekiguchi Kouhei
  • Fontaine Mathieu
  • Bando Yoshiaki
  • Yoshii Kazuyoshi
  , 2022. This paper describes a practical dual-process speech enhancement system that adapts environment-sensitive frame-online beamforming (front-end) with help from environment-free block-online source separation (back-end). To use minimum variance distortionless response (MVDR) beamforming, one may train a deep neural network (DNN) that estimates timefrequency masks used for computing the covariance matrices of sources (speech and noise). Backpropagation-based runtime adaptation of the DNN was proposed for dealing with the mismatched training-test conditions. Instead, one may try to directly estimate the source covariance matrices with a state-ofthe-art blind source separation method called fast multichannel non-negative matrix factorization (FastMNMF). In practice, however, neither the DNN nor the FastMNMF can be updated in a frame-online manner due to its computationally-expensive iterative nature. Our DNN-free system leverages the posteriors of the latest source spectrograms given by block-online FastMNMF to derive the current source covariance matrices for frame-online beamforming. The evaluation shows that our frame-online system can quickly respond to scene changes caused by interfering speaker movements and outperformed an existing block-online system with DNN-based beamforming by 5.0 points in terms of the word error rate.
• From Coherent Systems Technology to Advanced Fiber Sensing for Smart Network Monitoring
  
  • Dorize Christian
  • Guerrier Sterenn
  • Awwad Elie
  • Mardoyan Haik
  • Renaudier Jeremie
  Journal of Lightwave Technology, Institute of Electrical and Electronics Engineers (IEEE)/Optical Society of America(OSA), 2022, pp.1-10. (10.1109/JLT.2022.3221552)
  DOI : 10.1109/JLT.2022.3221552
• Listen to Interpret: Post-hoc Interpretability for Audio Networks with NMF
  
  • Jayneel Parekh
  • Sanjeel Parekh
  • Pavlo Mozharovskyi
  • Florence d'Alché-Buc
  • Richard Gael
  , 2022. This paper tackles post-hoc interpretability for audio processing networks. Our goal is to interpret decisions of a trained network in terms of high-level audio objects that are also listenable for the end-user. To this end, we propose a novel interpreter design that incorporates non-negative matrix factorization (NMF). In particular, a regularized interpreter module is trained to take hidden layer representations of the targeted network as input and produce time activations of pre-learnt NMF components as intermediate outputs. Our methodology allows us to generate intuitive audio-based interpretations that explicitly enhance parts of the input signal most relevant for a network's decision. We demonstrate our method's applicability on popular benchmarks, including a real-world multi-label classification task.
• Somme et produit, couple star
  
  • Zayana Karim
  • Rabiet Victor
  CultureMath, ENS, 2022. Relation entre somme et produit de deux nombres. Résolution des équations du second degré sans utiliser le discriminant
• Direction-Aware Adaptive Online Neural Speech Enhancement with an Augmented Reality Headset in Real Noisy Conversational Environments
  
  • Sekiguchi Kouhei
  • Nugraha Aditya Arie
  • Du Yicheng
  • Bando Yoshiaki
  • Fontaine Mathieu
  • Yoshii Kazuyoshi
  , 2022. This paper describes the practical response-and performance-aware development of online speech enhancement for an augmented reality (AR) headset that helps a user understand conversations made in real noisy echoic environments (e.g., cocktail party). One may use a state-of-the-art blind source separation method called fast multichannel nonnegative matrix factorization (FastMNMF) that works well in various environments thanks to its unsupervised nature. Its heavy computational cost, however, prevents its application to real-time processing. In contrast, a supervised beamforming method that uses a deep neural network (DNN) for estimating spatial information of speech and noise readily fits real-time processing, but suffers from drastic performance degradation in mismatched conditions. Given such complementary characteristics, we propose a dual-process robust online speech enhancement method based on DNN-based beamforming with FastMNMF-guided adaptation. FastMNMF (back end) is performed in a mini-batch style and the noisy and enhanced speech pairs are used together with the original parallel training data for updating the direction-aware DNN (front end) with backpropagation at a computationally-allowable interval. This method is used with a blind dereverberation method called weighted prediction error (WPE) for transcribing the noisy reverberant speech of a speaker, which can be detected from video or selected by a user's hand gesture or eye gaze, in a streaming manner and spatially showing the transcriptions with an AR technique. Our experiment showed that the word error rate was improved by more than 10 points with the runtime adaptation using only twelve minutes observation.
• Vibration Detection and Localization in Buried Fiber Cable after 80km of SSMF using Digital Coherent Sensing System with Co-Propagating 600Gb/s WDM Channels
  
  • Guerrier Sterenn
  • Benyahya Kaoutar
  • Dorize Christian
  • Awwad Elie
  • Mardoyan Haik
  • Renaudier Jérémie
  , 2022, pp.M2F.3. (10.1364/OFC.2022.M2F.3)
  DOI : 10.1364/OFC.2022.M2F.3
• Conditional and Relevant Common Information
  
  • Graczyk Robert
  • Lapidoth Amos
  • Wigger Michèle M
  Information and Inference, Oxford University Press (OUP), 2022, 11 (2), pp.679 - 737. Two variations on Wyner's common information are proposed: conditional common information and relevant common information. These are shown to have operational meanings analogous to those of Wyner's common information in appropriately defined distributed problems of compression, simulation and channel synthesis. For relevant common information, an additional operational meaning is identified: on a multiple-access channel with private and common messages, it is the minimal common-message rate that enables communication at the maximum sum-rate under a weak coordination constraint on the inputs and output. En route, the weak-coordination problem over a Gray-Wyner network is solved under the no-excess-rate constraint. (10.1093/imaiai/iaab021)
  DOI : 10.1093/imaiai/iaab021
• Optimizing Higher-Order Correlation Analysis Against Inner Product Masking Scheme
  
  • Ming Jingdian
  • Zhou Yongbin
  • Cheng Wei
  • Li Huizhong
  IEEE Transactions on Information Forensics and Security, Institute of Electrical and Electronics Engineers, 2022, 17, pp.3555-3568. (10.1109/TIFS.2022.3209890)
  DOI : 10.1109/TIFS.2022.3209890
• Variations on a Theme by Massey
  
  • Rioul Olivier
  IEEE Transactions on Information Theory, Institute of Electrical and Electronics Engineers, 2022, 68 (5), pp.2813-2828. In 1994, Jim Massey proposed the guessing entropy as a measure of the difficulty that an attacker has to guess a secret used in a cryptographic system, and established a well-known inequality between entropy and guessing entropy. Over 15 years before, in an unpublished work, he also established a well-known inequality for the entropy of an integer-valued random variable of given variance. In this paper, we establish a link between the two works by Massey in the more general framework of the relationship between discrete (absolute) entropy and continuous (differential) entropy. Two approaches are given in which the discrete entropy (or Rényi entropy) of an integer-valued variable can be upper bounded using the differential (Rényi) entropy of some suitably chosen continuous random variable. As an application, lower bounds on guessing entropy and guessing moments are derived in terms of entropy or Rényi entropy (without side information) and conditional entropy or Arimoto conditional entropy (when side information is available) (10.1109/TIT.2022.3141264)
  DOI : 10.1109/TIT.2022.3141264
• Free-Space Communication With Directly Modulated Mid-Infrared Quantum Cascade Devices
  
  • Spitz Olivier
  • Didier Pierre
  • Durupt Lauréline
  • Andrés Díaz-Thomas Daniel
  • Baranov Alexei N
  • Cerutti Laurent
  • Grillot Frédéric
  IEEE Journal of Selected Topics in Quantum Electronics, Institute of Electrical and Electronics Engineers, 2022. This study deals with the communication capabilities of two kinds of semiconductor lasers emitting in one of the atmosphere transparency windows, around 4 µm. One of these two lasers is a quantum cascade laser and the other one is an interband cascade laser. With the quantum cascade laser, a subsequent attenuation is added to the optical path in order to mimic the attenuation of free-space transmission of several kilometers. Direct electrical modulation is used to transmit the message and two-level formats, non-return-to-zero and return-to-zero, are used and compared in terms of maximum transmission data rate. The sensitivity to optical feedback is also analyzed, as well as the evolution of the error rate when reducing the optical power at the level of the detector. This work provides a novel insight into the development of future secure free-space optical communication links based on midinfrared semiconductor lasers and sheds the light on improvements required to achieve multi-Gbits/s communication with off-the-shelf components. Index Terms-Quantum cascade laser, interband cascade laser, mid-infrared photonics, free-space communication. I. INTRODUCTION T HE development of semiconductor laser technology was considerably boosted with inventing quantum cascade lasers (QCLs) in early 90s [1] and interband cascade lasers (ICLs) shortly afterwards [2]. At the early stages of QCLs, free-space optical transmissions were envisioned [3] alongside Manuscript (10.1109/JSTQE.2021.3096316)
  DOI : 10.1109/JSTQE.2021.3096316
• Survey of Exposure to RF Electromagnetic Fields in the Connected Car
  
  • Tognola Gabriella
  • Bonato Marta
  • Benini Martina
  • Aerts Sam
  • Gallucci Silvia
  • Chiaramello Emma
  • Fiocchi Serena
  • Parazzini Marta
  • Masini Barbara
  • Joseph Wout
  • Wiart Joe
  • Ravazzani Paolo
  IEEE Access, IEEE, 2022, 10, pp.47764-47781. Future vehicles will be increasingly connected to enable new applications and improve safety, traffic efficiency and comfort, through the use of several wireless access technologies, ranging from vehicle-to-everything (V2X) connectivity to automotive radar sensing and Internet of Things (IoT) technologies for intra-car wireless sensor networks. These technologies span the radiofrequency (RF) range, from a few hundred MHz as in intra-car network of sensors to hundreds of GHz as in automotive radars used for in-vehicle occupant detection and advanced driver assistance systems. Vehicle occupants and road users in the vicinity of the connected vehicle are thus daily immersed in a multi-source and multi-band electromagnetic field (EMF) generated by such technologies. This paper is the first comprehensive and specific survey about EMF exposure generated by the whole ensemble of connectivity technologies in cars. For each technology we describe the main characteristics, relevant standards, the application domain, and the typical deployment in modern cars. We then extensively describe the EMF exposure scenarios resulting from such technologies by resuming and comparing the outcomes from past studies on the exposure in the car. Results from past studies suggested that in no case EMF exposure was above the safe limits for the general population. Finally, open challenges for a more realistic characterization of the EMF exposure scenario in the connected car are discussed. (10.1109/ACCESS.2022.3170035)
  DOI : 10.1109/ACCESS.2022.3170035
• Unifying conditional and unconditional semantic image synthesis with OCO-GAN
  
  • Careil Marlène
  • Lathuilière Stéphane
  • Couprie Camille
  • Verbeek Jakob
  , 2022. Generative image models have been extensively studied in recent years. In the unconditional setting, they model the marginal distribution from unlabelled images. To allow for more control, image synthesis can be conditioned on semantic segmentation maps that instruct the generator the position of objects in the image. While these two tasks are intimately related, they are generally studied in isolation. We propose OCO-GAN, for Optionally COnditioned GAN, which addresses both tasks in a unified manner, with a shared image synthesis network that can be conditioned either on semantic maps or directly on latents. Trained adversarially in an end-to-end approach with a shared discriminator, we are able to leverage the synergy between both tasks. We experiment with Cityscapes, COCO-Stuff, ADE20K datasets in a limited data, semi-supervised and full data regime and obtain excellent performance, improving over existing hybrid models that can generate both with and without conditioning in all settings. Moreover, our results are competitive or better than state-of-the art specialised unconditional and conditional models.
• Custom Structure Preservation in Face Aging
  
  • Gomez-Trenado Guillermo
  • Lathuilière Stéphane
  • Mesejo Pablo
  • Cordón Óscar
  , 2022. In this work, we propose a novel architecture for face age editing that can produce structural modifications while maintaining relevant details present in the original image. We disentangle the style and content of the input image and propose a new decoder network that adopts a style-based strategy to combine the style and content representations of the input image while conditioning the output on the target age. We go beyond existing aging methods allowing users to adjust the degree of structure preservation in the input image during inference. To this purpose, we introduce a masking mechanism, the CUstom Structure Preservation module, that distinguishes relevant regions in the input image from those that should be discarded. CUSP requires no additional supervision. Finally, our quantitative and qualitative analysis which include a user study, show that our method outperforms prior art and demonstrates the effectiveness of our strategy regarding image editing and adjustable structure preservation. Code and pretrained models are available at https://github.com/guillermogotre/CUSP.