Sorry, you need to enable JavaScript to visit this website.
Partager

Publications

 

Les publications de nos enseignants-chercheurs sont sur la plateforme HAL :

 

Les publications des thèses des docteurs du LTCI sont sur la plateforme HAL :

 

Retrouver les publications figurant dans l'archive ouverte HAL par année :

2023

  • Iiro Honkala’s contributions to some conjectures on identifying codes
    • Hudry Olivier
    , 2023.
  • AI models for digital signal processing in future 6G-IoT networks
    • Larue Guillaume
    , 2023. Wireless technologies are of paramount importance to today's societies and future 6th generation communication networks are expected to address many societal and technological challenges. While communications infrastructures have a growing environmental impact that needs to be reduced, digital technologies also have a role to play in reducing the impact of all sectors of the economy. To this end, the future networks will not only have to enable more efficient information transfer, but also meet the growing need for data exchange capacity. This is particularly the role of the Internet of Things use cases, where a massive number of sensors allow to monitor complex systems. These use cases are associated with many constraints such as limited energy resources and complexity. Therefore, an efficient and low-complexity physical layer - responsible for the transmission of information between the network nodes - is absolutely crucial. In this regard, the use of artificial intelligence techniques is relevant. On the one hand, the mathematical framework of neural networks allows for efficient and low-cost generic hardware implementations. On the other hand, the application of learning procedures can improve the performance of certain algorithms. In this work, we are interested in the use of neural networks and machine learning for digital signal processing in the context of 6G-IoT networks. First, we are interested in the transcription of certain equalisation, demodulation and decoding algorithms from the digital communications literature into neural networks. Secondly, we are interested in the application of learning mechanisms on these neural network structures in order to improve their performance. A linear block decoder is proposed which allows the blind discovery of a decoding scheme whose performance is at least equivalent to that of the reference decoder. Finally, an end-to-end structure is presented, allowing joint learning of an encoding/decoding scheme with performance and complexity comparable to state-of-the-art solutions.
  • Function-valued regression with kernels : Improving speed, flexibility and robustness
    • Bouche Dimitri
    , 2023. With the increasing ubiquity of data-collecting devices, a great variety of phenomena is monitored with finer and finer accuracy, which constantly expands the scope of Machine Learning applications. Dealing with such volume of data efficiently is however challenging. Fortunately, as measurements get denser, they may become gradually redundant. We can then greatly reduce the burden by finding a representation which exploits properties of the generating process and/or is tailored for the application at hand.This thesis revolves around an aspect of this idea: functional data. Data indeed consist of discrete measurements, but sometimes thinking of those as functional, we can exploit prior knowledge on smoothness to obtain a better yet lower dimensional representation. The focus is on nonlinear models for functional output regression (FOR), relying on an extension of reproducing kernel Hilbert spaces for vector-valued functions (vv-RKHS), which is the cornerstone of many nonlinear existing FOR methods. We propose to challenge those in two aspects: their computational complexity with respect to the number of measurements per function and their focusing solely on the square loss.To that end, we introduce the new framework of kernel projection learning (KPL) combining vv-RKHSs and representation of signals in dictionaries. The loss remains functional, however the model predicts only a finite number of representation coefficients. This approach retains the many advantages of vv-RKHSs yet greatly alleviates the computational burden incurred by the functional outputs. We derive two estimators in closed-form using the square loss, one for fully observed functions and one for discretized ones. We show that both are consistent in terms of excess risk. We demonstrate as well the possibility to use other differentiable and convex losses, to combine this framework with large scale kernel methods and to automatically select the dictionary using a structured penalty.In another contribution, we propose to solve the regression problem in vv-RKHSs of function-valued functions for the family of convoluted losses which we introduce. Those losses can either promote sparsity or robustness with a parameter controlling the degree of locality of those properties. Thanks to their structure, they are particularly amenable to dual approaches which we investigate. We then overcome the challenges posed by the functional nature of the dual variables by proposing two possible representations and we propose corresponding algorithms.
  • Demonstration Of Performance For Low Cost Personal HSM
    • Urien Pascal
    , 2023, pp.879-880. This demonstration presents an original personal Hardware Secure Module (HSM) server, built from grid of secure elements and host system (Raspberry Pi), with internet connectivity. Each secure element is plugged in a board with a microcontroller providing I2C (Inter-Integrated Circuit) interface. The host system executes the open software IoSEv5 (Internet of Secure Elements version 5), which manages two T CP/IP daemons. First is used for downloading software in secure elements, second is a TLS front server that send/receive TLS packets to/from TLS backend servers running in secure elements. Applications hosted in secure elements implement a keystore, which stores cryptographic keys and computes signature over 256 bits elliptic curve. The demonstration shows the grid at work with 16 simultaneous TLS sessions performing signature operation. It shows that performance follows the Amdahl's law, with a speeding factor of about 50. (10.1109/CCNC51644.2023.10060586)
    DOI : 10.1109/CCNC51644.2023.10060586
  • Towards a centralized security architecture for SOME/IP automotive services
    • Khemissa Hamza
    • Urien Pascal
    , 2023, pp.977-978. Connected and autonomous vehicles (CAVs) consist of a number of networked computer components, called Electronic Control Units (ECUs). Scalable service-Oriented MiddlewarE over IP (SOME/IP) is a communication middleware standardized used to exchange various services between disjoint applications on distinct ECUs. However, it presents lack of authentication and confidentiality features. In this paper, we propose a centralized security architecture for SOME/IP automotive services. First, we present a lightweight symmetric cryptography based session key agreement scheme between each ECU and the manufacturer data center, which uses a random nonce, concatenation operator, a simple hash function and a keyedhash message authentication code (HMAC). Then, we define the security parameters between the different ECUs for the invehicle Ethernet-based communications. We propose the use of DTLS using pre-shared keys (DTLS-PSK) in order to secure the transmission of SOME/IP messages, (10.1109/CCNC51644.2023.10059950)
    DOI : 10.1109/CCNC51644.2023.10059950
  • Public-attention-based Adversarial Attack on Traffic Sign Recognition
    • Chi Lijun
    • Msahli Mounira
    • Memmi Gerard
    • Qiu Han
    , 2023, pp.740-745. Autonomous driving systems (ADS) can instantaneously and accurately recognize traffic signs by using deep neural networks (DNNs). Although adversarial attacks are well-known to easily fool DNNs by adding tiny but malicious perturbations, most attack methods require sufficient information about the victim models (white-box) to perform. In this paper, we propose a black-box attack in the recognition system of ADS, Public Attention Attacks (PAA), that can attack a black-box model by collecting the generic attention patterns of other white-box DNNs to transfer the attack. Particularly, we select multiple dual or triple attention patterns of white-box model combinations to generate the transferable adversarial perturbations for PAA attacks. We perform the experimentation on four well-trained models in different adversarial settings separately. The results indicate that when more white-box models the adversary collects to perform PAA, the higher the attack success rate (ASR) he can achieve to attack the target black-box model. (10.1109/CCNC51644.2023.10060485)
    DOI : 10.1109/CCNC51644.2023.10060485
  • Coalitional game-theoretical approach to coinvestment with application to edge computing
    • Patanè Rosario
    • Araldo Andrea
    • Chahed Tijani
    • Kiedanski Diego
    • Kofman Daniel
    , 2023, pp.517-522. We propose in this paper a coinvestment plan between several stakeholders of different types, namely a physical network owner, operating network nodes, e.g. a network operator or a tower company, and a set of service providers willing to use these resources to provide services as video streaming, augmented reality, autonomous driving assistance, etc. One such scenario is that of deployment of Edge Computing resources. Indeed, although the latter technology is ready, the high Capital Expenditure (CAPEX) cost of such resources is the barrier to its deployment. For this reason, a solid economical framework to guide the investment and the returns of the stakeholders is key to solve this issue. We formalize the coinvestment framework using coalitional game theory. We provide a solution to calculate how to divide the profits and costs among the stakeholders, taking into account their characteristics: traffic load, revenues, utility function. We prove that it is always possible to form the grand coalition composed of all the stakeholders, by showing that our game is convex. We derive the payoff of the stakeholders using the Shapley value concept, and elaborate on some properties of our game. We show our solution in simulation. (10.1109/CCNC51644.2023.10060093)
    DOI : 10.1109/CCNC51644.2023.10060093
  • Compressing Explicit Voxel Grid Representations: fast NeRFs become also small
    • Deng Chenxi Lola
    • Tartaglione Enzo
    , 2023, pp.1236-1245. (10.1109/WACV56688.2023.00129)
    DOI : 10.1109/WACV56688.2023.00129
  • Fuzzy Sets Methods in Image Processing and Understanding
    • Bloch Isabelle
    • Ralescu Anca
    , 2023. (10.1007/978-3-031-19425-2)
    DOI : 10.1007/978-3-031-19425-2
  • Solving stochastic weak Minty variational inequalities without increasing batch size
    • Pethick Thomas
    • Fercoq Olivier
    • Latafat Puya
    • Patrinos Panagiotis
    • Cevher Volkan
    , 2023. This paper introduces a family of stochastic extragradient-type algorithms for a class of nonconvex-nonconcave problems characterized by the weak Minty variational inequality (MVI). Unlike existing results on extragradient methods in the monotone setting, employing diminishing stepsizes is no longer possible in the weak MVI setting. This has led to approaches such as increasing batch sizes per iteration which can however be prohibitively expensive. In contrast, our proposed methods involves two stepsizes and only requires one additional oracle evaluation per iteration. We show that it is possible to keep one fixed stepsize while it is only the second stepsize that is taken to be diminishing, making it interesting even in the monotone setting. Almost sure convergence is established and we provide a unified analysis for this family of schemes which contains a nonlinear generalization of the celebrated primal dual hybrid gradient algorithm.
  • DNA code from cyclic and skew cyclic codes over F 4 [v]/⟨v 3 ⟩
    • Prakash Om
    • Singh Ashutosh
    • Verma Ram Krishna
    • Solé Patrick
    • Cheng Wei
    Entropy, MDPI, 2023. The main motivation of this work is to study and obtain some reversible and DNA codes of length n with better parameters. Here, we first investigate the structure of cyclic and skew cyclic codes over the chain ring R : = F 4 [ v ] / ⟨ v 3 ⟩ . We show an association between the codons and the elements of R using a Gray map. Under this Gray map, we study reversible and DNA codes of length n. Finally, several new DNA codes are obtained that have improved parameters than previously known codes. We also determine the Hamming and the Edit distances of these codes. (10.3390/e25020239)
    DOI : 10.3390/e25020239
  • Quadratic error bound of the smoothed gap and the restarted averaged primal-dual hybrid gradient
    • Fercoq Olivier
    Open Journal of Mathematical Optimization, Centre Mersenne, 2023, 4, pp.1-34. We study the linear convergence of the primal-dual hybrid gradient method. After a review of current analyses, we show that they do not explain properly the behavior of the algorithm, even on the most simple problems. We thus introduce the quadratic error bound of the smoothed gap, a new regularity assumption that holds for a wide class of optimization problems. Equipped with this tool, we manage to prove tighter convergence rates. Then, we show that averaging and restarting the primal-dual hybrid gradient allows us to leverage better the regularity constant. Numerical experiments on linear and quadratic programs, ridge regression and image denoising illustrate the findings of the paper. (10.5802/ojmo.26)
    DOI : 10.5802/ojmo.26
  • A Consistent Diffusion-Based Algorithm for Semi-Supervised Graph Learning
    • Bonald Thomas
    • de Lara Nathan
    , 2023. The task of semi-supervised classification aims at assigning labels to all nodes of a graph based on the labels known for a few nodes, called the seeds. One of the most popular algorithms relies on the principle of heat diffusion, where the labels of the seeds are spread by thermoconductance and the temperature of each node at equilibrium is used as a score function for each label. In this paper, we prove that this algorithm is not consistent unless the temperatures of the nodes at equilibrium are centered before scoring. This crucial step does not only make the algorithm provably consistent on a block model but brings significant performance gains on real graphs.
  • ADT: AI-Driven network Telemetry processing on routers
    • Foroughi Parisa
    • Brockners Frank
    • Rougier Jean-Louis
    Computer Networks, Elsevier, 2023, 220, pp.109474-1:109474-17. Network monitoring is a pivotal part of network management and operations. It is responsible for monitoring the behavior of the network to assure its functionality within expectation and to guarantee a smooth-running environment for enabling of various services. Therefore, operators are interested in gaining a comprehensive assessment of their network elements and tracking operational changes to facilitate timely correction of any deviation. Commonly, this assessment is achieved by performing regular manual checks of different operational counters and defining expert rules from known root causes. The common approach requires the maintenance of a regularly updated set of rules and only goes as far as the operator's pre-gained knowledge of the system. With the growing complexity of the networks as well as the availability of more data, a more efficient monitoring approach is necessary to address the emerging network monitoring requirements. In this paper, a novel unsupervised approach is proposed that is capable of exploring a broader set of counters (not limited to the handpicked Key Performance Indicators (KPIs)). The goal is to leverage the dependencies between the counters in order to discover complex state changes that might have otherwise slipped the operator's view. This paper proposes ADT, an AI-driven telemetry processing solution that facilitates monitoring of a larger set of counters. The Detector block of ADT is known as DESTIN, a multivariate unsupervised change detection for high dimensional time-series data of originally low effective dimension, which provides near real-time state assessment of network devices. The efficiency of the proposed approach is demonstrated and compared with well-known methodologies on an experimental test-bed. The method's performance is also explored extensively considering different criteria such as traffic type, device and the type of events to identify its potentials and limitations. The datasets used for the evaluation are made publicly available. (10.1016/j.comnet.2022.109474)
    DOI : 10.1016/j.comnet.2022.109474
  • Interband cascade technology for energy-efficient mid-infrared free-space communication
    • Didier Pierre
    • Knötig Hedwig
    • Spitz Olivier
    • Cerutti Laurent
    • Lardschneider Anna
    • Awwad Elie
    • Diaz-Thomas Daniel
    • Baranov A.
    • Weih Robert
    • Koeth Johannes
    • Schwarz Benedikt
    • Grillot Frédéric
    Photonics research, Optical Society of America, 2023, 11 (4), pp.582. Space-to-ground high-speed transmission is of utmost importance for the development of a worldwide broadband network. Mid-infrared wavelengths offer numerous advantages for building such a system, spanning from low atmospheric attenuation to eye-safe operation and resistance to inclement weather conditions. We demonstrate a full interband cascade system for high-speed transmission around a wavelength of 4.18 µm. The low-power consumption of both the laser and the detector in combination with a large modulation bandwidth and sufficient output power makes this technology ideal for a free-space optical communication application. Our proof-of-concept experiment employs a radio-frequency optimized Fabry–Perot interband cascade laser and an interband cascade infrared photodetector based on a type-II InAs/GaSb superlattice. The bandwidth of the system is evaluated to be around 1.5 GHz. It allows us to achieve data rates of 12 Gbit/s with an on–off keying scheme and 14 Gbit/s with a 4-level pulse amplitude modulation scheme. The quality of the transmission is enhanced by conventional pre- and post-processing in order to be compatible with standard error-code correction. (10.1364/PRJ.478776)
    DOI : 10.1364/PRJ.478776
  • Limitations of local update recovery in stabilizer-GKP codes: a quantum optimal transport approach
    • Koenig Robert
    • Rouzé Cambyse
    , 2023. Local update recovery seeks to maintain quantum information by applying local correction maps alternating with and compensating for the action of noise. Motivated by recent constructions based on quantum LDPC codes in the finite-dimensional setting, we establish an analytic upper bound on the fault-tolerance threshold for concatenated GKP-stabilizer codes with local update recovery. Our bound applies to noise channels that are tensor products of one-mode beamsplitters with arbitrary environment states, capturing, in particular, photon loss occurring independently in each mode. It shows that for loss rates above a threshold given explicitly as a function of the locality of the recovery maps, encoded information is lost at an exponential rate. This extends an early result by Razborov from discrete to continuous variable (CV) quantum systems. To prove our result, we study a metric on bosonic states akin to the Wasserstein distance between two CV density functions, which we call the bosonic Wasserstein distance. It can be thought of as a CV extension of a quantum Wasserstein distance of order 1 recently introduced by De Palma et al. in the context of qudit systems, in the sense that it captures the notion of locality in a CV setting. We establish several basic properties, including a relation to the trace distance and diameter bounds for states with finite average photon number. We then study its contraction properties under quantum channels, including tensorization, locality and strict contraction under beamsplitter-type noise channels. Due to the simplicity of its formulation, and the established wide applicability of its finite-dimensional counterpart, we believe that the bosonic Wasserstein distance will become a versatile tool in the study of CV quantum systems. (10.48550/arXiv.2309.16241)
    DOI : 10.48550/arXiv.2309.16241
  • MPEG immersive video
    • Garus Patrick
    • Milovanović Marta
    • Jung Joël
    • Cagnazzo Marco
    , 2023, pp.327-356. MPEG immersive video (MIV) is a novel standard, enabling the compression of volumetric video content. In this chapter, we describe MIV, its tools, and its profiles. Given that MIV is a video-based solution, the texture and geometry information is coded using available 2D video codecs, which are independent of MIV. We present the performance of MIV with several state-of-the-art 2D codecs: VVC, AV1, and AVS3, highlighting that the eventual success of MIV does not depend on the market share of any particular 2D codec. However, using suitable tools for the coding of MIV texture or depth map atlases is an important requirement for efficient compression of immersive video. In this context, we present results related to screen content coding tools of VVC and show their potential for the compression of MIV atlases. (10.1016/B978-0-32-391755-1.00018-3)
    DOI : 10.1016/B978-0-32-391755-1.00018-3
  • Efficient learning of the structure and parameters of local Pauli noise channels
    • Rouzé Cambyse
    • Stilck Franca Daniel
    , 2023. The unavoidable presence of noise is a crucial roadblock for the development of large-scale quantum computers and the ability to characterize quantum noise reliably and efficiently with high precision is essential to scale quantum technologies further. Although estimating an arbitrary quantum channel requires exponential resources, it is expected that physically relevant noise has some underlying local structure, for instance that errors across different qubits have a conditional independence structure. Previous works showed how it is possible to estimate Pauli noise channels with an efficient number of samples in a way that is robust to state preparation and measurement errors, albeit departing from a known conditional independence structure. We present a novel approach for learning Pauli noise channels over n qubits that addresses this shortcoming. Unlike previous works that focused on learning coefficients with a known conditional independence structure, our method learns both the coefficients and the underlying structure. We achieve our results by leveraging a groundbreaking result by Bresler for efficiently learning Gibbs measures and obtain an optimal sample complexity of O(log(n)) to learn the unknown structure of the noise acting on n qubits. This information can then be leveraged to obtain a description of the channel that is close in diamond distance from O(poly(n)) samples. Furthermore, our method is efficient both in the number of samples and postprocessing without giving up on other desirable features such as SPAM-robustness, and only requires the implementation of single qubit Cliffords. In light of this, our novel approach enables the large-scale characterization of Pauli noise in quantum devices under minimal experimental requirements and assumptions. (10.48550/arXiv.2307.02959)
    DOI : 10.48550/arXiv.2307.02959
  • Integration of heterogeneous components for co-simulation
    • Jerray Jawher
    • Ameur-Boulifa Rabéa
    • Apvrille Ludovic
    , 2023. Because of their complexity, embedded systems are designed with sub-systems or components taken in charge by different development teams or entities and with different modeling frameworks and simulation tools, depending on the characteristics of each component. Unfortunately, this diversity of tools and semantics makes the integration of these heterogeneous components difficult. Thus, to evaluate their integration before their hardware or software is available, one solution would be to merge them into a common modeling framework. Yet, such a holistic environment supporting many computation and computation semantics seems hard to settle. Another solution we investigate in this paper is to generically link their respective simulation environments in order to keep the strength and semantics of each component environment. The paper presents a method to simulate heterogeneous components of embedded systems in real-time. These components can be described at any abstraction level. Our main contribution is a generic glue that can analyze in real-time the state of different simulation environments and accordingly enforce the correct communication semantics between components. Once presented in a generic way, our glue is illustrated with Apache Kafka as the communication facility between simulation engines. It is then applied to two model and simulation frameworks: TTool and SystemC. Finally, Zigbee serves as a case study to illustrate the strengths of our approach.
  • (Adversarial) Electromagnetic Disturbance in the Industry
    • Beckers Arthur
    • Guilley Sylvain
    • Maurine Philippe
    • O'Flynn Colin
    • Picek Stjepan
    IEEE Transactions on Computers, Institute of Electrical and Electronics Engineers, 2023, 72 (2), pp.414-422. Faults occur naturally and are responsible for reliability concerns. Faults are also an interesting tool for attackers to extract sensitive information from secure chips. In particular, non-invasive fault attacks have received a fair amount of attention. One easy way to perturb a chip without altering it is the so-called Electromagnetic Fault Injection (EMFI). Such attack has been studied in great depth, and nowadays, it is part and parcel of the state-of-the-art. Indeed, new capabilities have emerged where EM experimental benches are used to cryptanalyze chips. The progress of this "field" is fast, in terms of reproducibility, accuracy, and number of use-cases. However, there is too little awareness about such advances. In this paper, we aim to expose the true harmfulness of EMFI (including reproducibility) to enable reasonable security quotations. We also analyze protections (at hardware/firmware/system levels) in light of their efficiency. We characterize the specificity of EM fault injection compared to other injection means (laser, glitch, probing). (10.1109/TC.2022.3224373)
    DOI : 10.1109/TC.2022.3224373
  • PrivacyGAN: robust generative image privacy
    • Zameshina Mariia
    • Careil Marlene
    • Teytaud Olivier
    • Najman Laurent
    , 2023. Classical techniques for protecting facial image privacy typically fall into two categories: data-poisoning methods, exemplified by Fawkes, which introduce subtle perturbations to images, or anonymization methods that generate images resembling the original only in several characteristics, such as gender, ethnicity, or facial expression. In this study, we introduce a novel approach, PrivacyGAN, that uses the power of image generation techniques, such as VQGAN and StyleGAN, to safeguard privacy while maintaining image usability, particularly for social media applications. Drawing inspiration from Fawkes, our method entails shifting the original image within the embedding space towards a decoy image. We evaluate our approach using privacy metrics on traditional and novel facial image datasets. Additionally, we propose new criteria for evaluating the robustness of privacy-protection methods against unknown image recognition techniques, and we demonstrate that our approach is effective even in unknown embedding transfer scenarios. We also provide a human evaluation that further proves that the modified image preserves its utility as it remains recognisable as an image of the same person by friends and family.
  • Execution trace analysis for a precise understanding of latency violations
    • Zoor Maysam
    • Apvrille Ludovic
    • Pacalet Renaud
    • Coudert Sophie
    Software and Systems Modeling, Springer Verlag, 2023. Despite the amount of proposed works for the verification of embedded systems, understanding the root cause of violations of requirements in simulation or execution traces is still an openissue, especially when dealing with temporal properties such as latencies. Is the violation due to an unfavorable real-time scheduling, to contentions on buses, to the characteristics of functional algorithms or hardware components? The paper introduces the Precise Latency ANalysis approach (PLAN), a new trace analysis technique whose objective is to classify execution transactions according to their impact on latency. To do so, we rely first on a model transformation that builds up a dependency graph from an allocation model, thus including hardware and software aspects of a system model. Then, from this graph and an execution trace, our analysis can highlight how software or hardware elements contributed to the latency violation. The paper first formalizes the problem before applying our approach to simulation traces of SysML models. A case study defined in the AQUAS European project illustrates the relevance of our approach. Last, a performance evaluation gives computation times for several models and requirements. (10.1007/s10270-022-01076-z)
    DOI : 10.1007/s10270-022-01076-z
  • Scaling by subsampling for big data, with applications to statistical learning
    • Bertail Patrice
    • Bouchouia Mohammed
    • Jelassi Ons
    • Tressou Jessica
    • Zetlaoui Mélanie
    Journal of Nonparametric Statistics, American Statistical Association, 2023, 36 (1), pp.78-117. Handling large datasets and calculating complex statistics on huge datasets require important computing resources. Using subsampling methods to calculate statistics of interest on small samples is often used in practice to reduce computational complexity, for instance using the divide and conquer strategy. In this article, we recall some results on subsampling distributions and derive a precise rate of convergence for these quantities and the corresponding quantiles. We also develop some standardization techniques based on subsampling unstandardized statistics in the framework of large datasets. It is argued that using several subsampling distributions with different subsampling sizes brings a lot of information on the behavior of statistical learning procedures: subsampling allows to estimate the rate of convergence of different algorithms, to estimate the variability of complex statistics, to estimate confidence intervals for out-of-sample errors and interpolate their values at larger scales. These results are illustrated on simulations, but also on two important datasets, frequently analyzed in the statistical learning community, EMNIST (recognition of digits) and VeReMi (analysis of Network Vehicular Reference Misbehavior). (10.1080/10485252.2023.2219782)
    DOI : 10.1080/10485252.2023.2219782
  • Knowledge Bases and Language Models: Complementing Forces
    • Suchanek Fabian M.
    • Luu Anh Tuan
    , 2023. Large language models (LLMs), as a particular instance of generative articial intelligence, have revolutionized natural language processing. In this invited paper, we argue that LLMs are complementary to structured data repositories such as databases or knowledge bases, which use symbolic knowledge representations. Hence, the two ways of knowledge representation will likely continue to co-exist, at least in the near future. We discuss ways that have been explored to make the two approaches work together, and point out opportunities and challenges for their symbiosis.
  • Contrast, Stylize and Adapt: Unsupervised Contrastive Learning Framework for Domain Adaptive Semantic Segmentation
    • Li Tianyu
    • Roy Subhankar
    • Zhou Huayi
    • Lu Hongtao
    • Lathuilière Stéphane
    , 2023. To overcome the domain gap between synthetic and real-world datasets, unsupervised domain adaptation methods have been proposed for semantic segmentation. Majority of the previous approaches have attempted to reduce the gap either at the pixel or feature level, disregarding the fact that the two components interact positively. To address this, we present CONtrastive FEaTure and pIxel alignment (CONFETI) for bridging the domain gap at both the pixel and feature levels using a unique contrastive formulation. We introduce well-estimated prototypes by including category-wise cross-domain information to link the two alignments: the pixel-level alignment is achieved using the jointly trained style transfer module with the prototypical semantic consistency, while the feature-level alignment is enforced to cross-domain features with the \textbf{pixel-to-prototype contrast}. Our extensive experiments demonstrate that our method outperforms existing state-of-the-art methods using DeepLabV2. Our code is available at https://github.com/cxa9264/CONFETI