Publications

2025

• Self-Supervision Enhances Instance-based Multiple Instance Learning Methods in Digital Pathology: A Benchmark Study
  
  • Mammadov Ali
  • Le Folgoc Loic
  • Adam Julien
  • Buronfosse Anne
  • Hayem Gilles
  • Hocquet Guillaume
  • Gori Pietro
  Journal of Medical Imaging, SPIE Digital Library, 2025. Multiple Instance Learning (MIL) has emerged as the best solution for Whole Slide Image (WSI) classification. It consists of dividing each slide into patches, which are treated as a bag of instances labeled with a global label. MIL includes two main approaches: instance-based and embedding-based. In the former, each patch is classified independently, and then the patch scores are aggregated to predict the bag label. In the latter, bag classification is performed after aggregating patch embeddings. Even if instance-based methods are naturally more interpretable, embedding-based MILs have usually been preferred in the past due to their robustness to poor feature extractors. However, recently, the quality of feature embeddings has drastically increased using self-supervised learning (SSL). Nevertheless, many authors continue to endorse the superiority of embedding-based MIL. To investigate this further, we conduct 710 experiments across 4 datasets, comparing 10 MIL strategies, 6 self-supervised methods with 4 backbones, 4 foundation models, and various pathology-adapted techniques. Furthermore, we introduce 4 instance-based MIL methods never used before in the pathology domain. Through these extensive experiments, we show that with a good SSL feature extractor, simple instance-based MILs, with very few parameters, obtain similar or better performance than complex, state-of-the-art (SOTA) embedding-based MIL methods, setting new SOTA results on the BRACS and Camelyon16 datasets. Since simple instance-based MIL methods are naturally more interpretable and explainable to clinicians, our results suggest that more effort should be put into well-adapted SSL methods for WSI rather than into complex embedding-based MIL methods.
• The role of Mrs. Gerber’s Lemma for evaluating the information leakage of secret sharing schemes
  
  • Rioul Olivier
  • Béguinot Julien
  , 2025.
• Exact distinguishability between real-valued and complex-valued Haar random quantum states
  
  • Nemoz Tristan
  • Alléaume Romain
  • Brown Peter
  Quantum, Verein zur Förderung des Open Access Publizierens in den Quantenwissenschaften, 2025, 10, pp.2120. Haar random states are fundamental objects in quantum information theory and quantum computing. We study the density matrix resulting from sampling $t$ copies of a $d$-dimensional quantum state according to the Haar measure on the orthogonal group. In particular, we analytically compute its spectral decomposition. This allows us to compute exactly the trace distance between $t$-copies of a real Haar random state and $t$-copies of a complex Haar random state. Using this we show a lower-bound on the approximation parameter of real-valued state $t$-designs and improve the lower-bound on the number of copies required for imaginarity testing. (10.22331/q-2026-05-29-2120)
  DOI : 10.22331/q-2026-05-29-2120
• Rate Meta-Distribution in Millimeter Wave URLLC Device-to-Device Networks With Beam Misalignment
  
  • Quan Yibo
  • Coupechoux Marceau
  • Kélif Jean-Marc
  IEEE Transactions on Vehicular Technology, Institute of Electrical and Electronics Engineers, 2025, 74 (1), pp.657-673. <div><p>Using the stochastic geometry framework, we study a millimeter wave (mmWave) Device-to-Device (D2D) network dedicated to Ultra-Reliable Low Latency Communications (URLLC), where users employ multiple antennas to perform beamforming. We leverage the notion of meta-distribution in order to capture the reliability requirement of URLLC. The packet transmission process is divided into two phases: a beam training phase, during which exhaustive beam sweeping is adopted, and a data transmission phase. The paper investigates the misalignment error distribution resulting from an imperfect training phase, due to the finite codebooks resolution and the fast variation of the channel. For the data transmission phase, closed-form expressions for all the moments of the conditional rate coverage probability are derived, and the meta-distribution is approximated using the beta approximation. The study evaluates the overall network performance through the effective rate metadistribution, which accounts for the training overhead and beam misalignment errors. The results show the detrimental impact of misalignment errors when URLLC requirements are stringent and highlight the trade-off between the training overhead and the gain brought by multiple antennas. Insights are provided for optimally and jointly choosing the codebook size and tbe number of antennas.</p></div> (10.1109/TVT.2024.3451487)
  DOI : 10.1109/TVT.2024.3451487
• ding-01 :ARG0 Un corpus AMR pour le français parlé spontané
  
  • Kang Jeongwoo
  • Boritchev Maria
  • Coavoux Maximin
  , 2025, pp.791-801. Nous présentons notre travail en cours sur l'annotation d'un corpus sémantique du français. Nous annotons le corpus DinG, constitué de transcriptions de dialogues spontanés en français enregistrées pendant des parties du jeu de plateau Catan , en Abstract Meaning Representation (AMR), un formalisme de représentation sémantique. Comme AMR a une couverture insuffisante de la dynamique de la parole spontanée, nous étendons le formalisme pour mieux représenter la parole spontanée et les structures de phrases spécifiques au français. En outre, nous diffusons un guide d'annotation détaillant ces extensions. Enfin, nous publions notre corpus sous licence libre (CC-SA-BY). Notre travail contribue au développement de ressources sémantiques pour le dialogue en français.
• Just Project! Multi-Channel Despeckling, the Easy Way
  
  • Denis Loïc
  • Dalsasso Emanuele
  • Tupin Florence
  IEEE Transactions on Geoscience and Remote Sensing, Institute of Electrical and Electronics Engineers, 2025, 63, pp.1-11. Reducing speckle fluctuations in multi-channel SAR images is essential in many applications of SAR imaging such as polarimetric classification or interferometric height estimation. While single-channel despeckling has widely benefited from the application of deep learning techniques, extensions to multi-channel SAR images are much more challenging. This paper introduces MuChaPro, a generic framework that exploits existing single-channel despeckling methods. The key idea is to generate numerous single-channel projections, restore these projections, and recombine them into the final multi-channel estimate. This simple approach is shown to be effective in polarimetric and/or interferometric modalities. A special appeal of MuChaPro is the possibility to apply a self-supervised training strategy to learn sensor-specific networks for single-channel despeckling. (10.1109/TGRS.2025.3531957)
  DOI : 10.1109/TGRS.2025.3531957
• A bipartite ranking approach to the two-sample problem
  
  • Clémençon Stéphan
  • Limnios Myrto
  • Vayatis Nicolas
  Electronic Journal of Statistics, Shaker Heights, OH : Institute of Mathematical Statistics, 2025, 19 (1), pp.2733–2779. The two-sample problem consists in testing whether two independent samples are drawn from the same (unknown) distribution. Its study in high-dimension is the subject of much attention, especially because the information acquisition processes at work in the Big Data era often involve various poorly controlled sources, leading to datasets possibly exhibiting strong sampling bias. While the efficiency of classic methods relying on computing a discrepancy measure between the empirical distributions of each sample, is negatively impacted by increasing dimensionality, we develop a two-step approach based on statistical learning and an extension of rank tests. By dividing the initial samples in two, a bipartite ranking algorithm first learns a real-valued scoring function inducing a preorder on the multivariate space. Then, a rank statistic based on the scores of the remaining observations, tests for differences in distribution. Because the ranking algorithm learns how to map the data onto the real line as the likelihood ratio between the original multivariate distributions, the approach resists to large dimensions (ignoring ranking model bias issues) and preserves the advantages of univariate rank tests. We prove nonasymptotic error bounds based on recent results for two-sample linear rank-processes, and experimentally show how the promoted approach surpasses state-of-the-art methods. (10.1214/25-EJS2392)
  DOI : 10.1214/25-EJS2392