Publications

2022

• 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
• 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.
• A general sample complexity analysis of vanilla policy gradient
  
  • Yuan Rui
  • Gower Robert M
  • Lazaric Alessandro
  , 2022. We adapt recent tools developed for the analysis of Stochastic Gradient Descent (SGD) in non-convex optimization to obtain convergence and sample complexity guarantees for the vanilla policy gradient (PG). Our only assumptions are that the expected return is smooth w.r.t. the policy parameters, that its H-step truncated gradient is close to the exact gradient, and a certain ABC assumption. This assumption requires the second moment of the estimated gradient to be bounded by A ≥ 0 times the suboptimality gap, B ≥ 0 times the norm of the full batch gradient and an additive constant C ≥ 0, or any combination of aforementioned. We show that the ABC assumption is more general than the commonly used assumptions on the policy space to prove convergence to a stationary point. We provide a single convergence theorem that recovers the O(−4) sample complexity of PG. Our results also affords greater flexibility in the choice of hyper parameters such as the step size and places no restriction on the batch size m, including the single trajectory case (i.e., m = 1). We then instantiate our theorem in different settings, where we both recover existing results and obtained improved sample complexity, e.g., for convergence to the global optimum for Fisher-nondegenerated parameterized policies.
• Dominating, Locating-Dominating and Identifying Codes in the q-ary Lee Hypercube
  
  • Hudry Olivier
  • Charon Irene
  • Lobstein Antoine
  , 2022.
• FAST STRATEGIES FOR MULTI-TEMPORAL SPECKLE REDUCTION OF SENTINEL-1 GRD IMAGES
  
  • Meraoumia Inès
  • Dalsasso Emanuele
  • Denis Loïc
  • Tupin Florence
  , 2022. Reducing speckle and limiting the variations of the physical parameters in Synthetic Aperture Radar (SAR) images is often a key-step to fully exploit the potential of such data. Nowadays, deep learning approaches produce state of the art results in single-image SAR restoration. Nevertheless, huge multi-temporal stacks are now often available and could be efficiently exploited to further improve image quality. This paper explores two fast strategies employing a singleimage despeckling algorithm, namely SAR2SAR [1], in a multi-temporal framework. The first one is based on Quegan filter [2] and replaces the local reflectivity pre-estimation by SAR2SAR. The second one uses SAR2SAR to suppress speckle from a ratio image encoding the multi-temporal information under the form of a "super-image", i.e. the temporal arithmetic mean of a time series. Experimental results on Sentinel-1 GRD data show that these two multi-temporal strategies provide improved filtering results while adding a limited computational cost. (10.1109/IGARSS46834.2022.9883448)
  DOI : 10.1109/IGARSS46834.2022.9883448
• Approximate Bayesian computation with the sliced-Wasserstein distance
  
  • Nadjahi Kimia
  • de Bortoli Valentin
  • Durmus Alain
  • Badeau Roland
  • Şimşekli Umut
  , 2022. Approximate Bayesian Computation (ABC) is a popular method for approximate inference in generative models with intractable but easy-to-sample likelihood. It constructs an approximate posterior distribution by finding parameters for which the simulated data are close to the observations in terms of summary statistics. These statistics are defined beforehand and might induce a loss of information, which has been shown to deteriorate the quality of the approximation. To overcome this problem, Wasserstein-ABC has been recently proposed, and compares the datasets via the Wasserstein distance between their empirical distributions, but does not scale well to the dimension or the number of samples. We propose a new ABC technique, called Sliced-Wasserstein ABC and based on the Sliced-Wasserstein distance, which has better computational and statistical properties. We derive two theoretical results showing the asymptotical consistency of our approach, and we illustrate its advantages on synthetic data and an image denoising task. (10.1109/icassp40776.2020.9054735)
  DOI : 10.1109/icassp40776.2020.9054735
• A User Centric Blockage Model for Wireless Networks
  
  • Baccelli François
  • Liu Bin
  • Decreusefond Laurent
  • Song Rongfang
  IEEE Transactions on Wireless Communications, Institute of Electrical and Electronics Engineers, 2022, 21 (10), pp.10 p.. This paper proposes a cascade blockage model for analyzing the vision that a user has of a wireless network. This model, inspired by the classical multiplicative cascade models, has a radial structure meant to analyze blockages seen by the receiver at the origin in different angular sectors. The main novelty is that it is based on the geometry of obstacles and takes the joint blockage phenomenon into account. We show on a couple of simple instances that the Laplace transforms of total interference satisfies a functional equation that can be solved efficiently by an iterative scheme. This is used to analyze the coverage probability of the receiver and the effect of blockage correlation and penetration loss in both dense and sparse blockage environments. Furthermore, this model is used to investigate the effect of blockage correlation on user beamforming techniques. Another functional equation and its associated iterative algorithm are proposed to derive the coverage performance of the best beam selection in this context. In addition, the conditional coverage probability is also derived to evaluate the effect of beam switching. The results not only show that beam selection is quite efficient for multi-beam terminals, but also show how the correlation brought by blockages can be leveraged to accelerate beam sweeping and pairing. (10.1109/TWC.2022.3166211)
  DOI : 10.1109/TWC.2022.3166211
• Negative Sampling Strategies for Contrastive Self-Supervised Learning of Graph Representations
  
  • Hafidi Hakim
  • Ghogho Mounir
  • Ciblat Philippe
  • Swami Ananthram
  Signal Processing, Elsevier, 2022, 190 (4). Contrastive learning has become a successful approach for learning powerful text and image representations in a self-supervised manner. Contrastive frameworks learn to distinguish between representations coming from augmentations of the same data point (positive pairs) and those of other (negative) examples. Recent studies aim at extending methods from contrastive learning to graph data. In this work, we propose a general framework for learning node representations in a self supervised manner called Graph Constrastive Learning (GraphCL). It learns node embeddings by maximizing the similarity between the nodes representations of two randomly perturbed versions of the same graph. We use graph neural networks to produce two representations of the same node and leverage a contrastive learning loss to maximize agreement between them. We investigate different standard and new negative sampling strategies as well as a comparison without negative sampling approach. We demonstrate that our approach significantly outperforms the state-of-the-art in unsupervised learning on a number of node classification benchmarks in both transductive and inductive learning setups.
• Video-to-Music Recommendation using Temporal Alignment of Segments
  
  • Prétet Laure
  • Richard Gael
  • Souchier Clément
  • Peeters Geoffroy
  IEEE Transactions on Multimedia, Institute of Electrical and Electronics Engineers, 2022.
• As if by magic: self-supervised training of deep despeckling networks with MERLIN
  
  • Dalsasso Emanuele
  • Denis Loïc
  • Tupin Florence
  IEEE Transactions on Geoscience and Remote Sensing, Institute of Electrical and Electronics Engineers, 2022, 60, pp.1-13. Speckle fluctuations seriously limit the interpretability of synthetic aperture radar (SAR) images. Speckle reduction has thus been the subject of numerous works spanning at least four decades. Techniques based on deep neural networks have recently achieved a new level of performance in terms of SAR image restoration quality. Beyond the design of suitable network architectures or the selection of adequate loss functions, the construction of training sets is of uttermost importance. So far, most approaches have considered a supervised training strategy: the networks are trained to produce outputs as close as possible to speckle-free reference images. Speckle-free images are generally not available, which requires resorting to natural or optical images or the selection of stable areas in long time series to circumvent the lack of ground truth. Self-supervision, on the other hand, avoids the use of speckle-free images. We introduce a self-supervised strategy based on the separation of the real and imaginary parts of single-look complex (SLC) SAR images, called coMplex sElf-supeRvised despeckLINg (MERLIN), and show that it offers a straightforward way to train all kinds of deep despeckling networks. Networks trained with MERLIN take into account the spatial correlations due to the SAR transfer function specific to a given sensor and imaging mode. By requiring only a single image, and possibly exploiting large archives, MERLIN opens the door to hassle-free as well as large-scale training of despeckling networks. The code of the trained models is made freely available at https://gitlab.telecom-paris.fr/RING/MERLIN . (10.1109/TGRS.2021.3128621)
  DOI : 10.1109/TGRS.2021.3128621
• Delaunay Painting: Perceptual image coloring from raster contours with gaps
  
  • Parakkat Amal Dev
  • Memari Pooran
  • Cani Marie-Paule
  Computer Graphics Forum, Wiley, 2022. We introduce Delaunay Painting, a novel and easy-to-use method to flat-color contour-sketches with gaps. Starting from a Delaunay triangulation of the input contours, triangles are iteratively filled with the appropriate colors, thanks to the dynamic update of flow values calculated from color hints. Aesthetic finish is then achieved, through energy minimisation of contour curves and further heuristics enforcing the appropriate sharp corners. To be more efficient, the user can also make use of our color diffusion framework which automatically extends coloring to small, internal regions such as those delimited by hatches. The resulting method robustly handles input contours with strong gaps. As an interactive tool, it minimizes user's efforts and enables any coloring strategy, as the result does not depend on the order of interactions. We also provide an automatized version of the coloring strategy for quick segmentation of contours images, that we illustrate with an application to medical imaging.
• M A T R I X Transpositions. Spécial Prod : de l’autre côté du miroir
  
  • Zayana Karim
  • Boyer Ivan
  • Massard Marc-Aurèle
  • Rabiet Victor
  CultureMath, ENS, 2022.
• SELF ATTENTION DEEP GRAPH CNN CLASSIFICATION OF TIMES SERIES IMAGES FOR LAND COVER MONITORING
  
  • Chaabane Ferdaous
  • Réjichi Safa
  • Tupin Florence
  , 2022. Time Series of Satellite Imagery (SITS) acquired by recent Earth observation systems represent an important source of information that supports several remote sensing applications related to monitoring the dynamics of the Earth's surface over large areas. A major challenge then is to design new deep learning models that can take into account intelligently the complementarity between temporal and spatial contexts that characterize these data structures. In this work, we propose to use an adapted self-attention convolutional neural network for spatio-temporal graphs classification that exploits both spatial and temporal dimensions. The graphs will be generated from a series of temporal images that are segmented into different regions. Those graphs are then classified using the Self-Attention Deep Graph CNN (DGCNN) model to highlight the temporal evolution of land cover areas through the construction of a spatio-temporal Map.
• A Review of Machine Learning Techniques in Analog Integrated Circuit Design Automation
  
  • Mina Rayan
  • Jabbour Chadi
  • Sakr George E
  Electronics, MDPI, 2022, 11 (3), pp.435. Analog integrated circuit design is widely considered a time-consuming task due to the acute dependence of analog performance on the transistors’ and passives’ dimensions. An important research effort has been conducted in the past decade to reduce the front-end design cycles of analog circuits by means of various automation approaches. On the other hand, the significant progress in high-performance computing hardware has made machine learning an attractive and accessible solution for everyone. The objectives of this paper were: (1) to provide a comprehensive overview of the existing state-of-the-art machine learning techniques used in analog circuit sizing and analyze their effectiveness in achieving the desired goals; (2) to point out the remaining open challenges, as well as the most relevant research directions to be explored. Finally, the different analog circuits on which machine learning techniques were applied are also presented and their results discussed from a circuit designer perspective. (10.3390/electronics11030435)
  DOI : 10.3390/electronics11030435
• What are the best systems? New perspectives on NLP Benchmarking
  
  • Irurozki Ekhine
  • Colombo Pierre
  • Noiry Nathan
  • Clémençon Stéphan
  , 2022. In Machine Learning, a benchmark refers to an ensemble of datasets associated with one or multiple metrics together with a way to aggregate different systems performances. They are instrumental in (i) assessing the progress of new methods along different axes and (ii) selecting the best systems for practical use. This is particularly the case for NLP with the development of large pre-trained models (e.g. GPT, BERT) that are expected to generalize well on a variety of tasks. While the community mainly focused on developing new datasets and metrics, there has been little interest in the aggregation procedure, which is often reduced to a simple average over various performance measures. However, this procedure can be problematic when the metrics are on a different scale, which may lead to spurious conclusions. This paper proposes a new procedure to rank systems based on their performance across different tasks. Motivated by the social choice theory, the final system ordering is obtained through aggregating the rankings induced by each task and is theoretically grounded. We conduct extensive numerical experiments (on over 270k scores) to assess the soundness of our approach both on synthetic and real scores (e.g. GLUE, EXTREM, SEVAL, TAC, FLICKR). In particular, we show that our method yields different conclusions on state-of-the-art systems than the mean-aggregation procedure while being both more reliable and robust
• Curves on Frobenius classical surfaces in $\mathbb{P}^{3}$ over finite fields
  
  • Berardini Elena
  • Nardi Jade
  Acta Arithmetica, Instytut Matematyczny PAN, 2022, 205 (4), pp.323-340. (10.4064/aa211118-12-9)
  DOI : 10.4064/aa211118-12-9
• Comparing Deep Models and Evaluation Strategies for Multi-Pitch Estimation in Music Recordings
  
  • Weis Christof
  • Peeters Geoffroy
  IEEE/ACM Transactions on Audio, Speech and Language Processing, Institute of Electrical and Electronics Engineers, 2022, 30, pp.2814-2827. (10.1109/TASLP.2022.3200547)
  DOI : 10.1109/TASLP.2022.3200547
• Conditional independence testing via weighted partial copulas and nearest neighbors
  
  • Bianchi Pascal
  • Elgui Kevin
  • Portier François
  Journal of Multivariate Analysis, Elsevier, 2022, 30 (3), pp.1117-1147. This paper introduces the \textit{weighted partial copula} function for testing conditional independence. The proposed test procedure results from these two ingredients: (i) the test statistic is an explicit Cramer-von Mises transformation of the \textit{weighted partial copula}, (ii) the regions of rejection are computed using a bootstrap procedure which mimics conditional independence by generating samples from the product measure of the estimated conditional marginals. Under conditional independence, the weak convergence of the \textit{weighted partial copula proces}s is established when the marginals are estimated using a smoothed local linear estimator. Finally, an experimental section demonstrates that the proposed test has competitive power compared to recent state-of-the-art methods such as kernel-based test.