Christian Gagné

Biographie

Christian Gagné est professeur au Département de génie électrique et de génie informatique de l’Université Laval depuis 2008, et dirige l’Institut intelligence et données (IID). Il détient une chaire en IA Canada-CIFAR et est membre associé à Mila – Institut québécois d’intelligence artificielle. Il est également membre du Laboratoire de vision et systèmes numériques (LVSN), une composante du Centre de recherche en robotique, vision et intelligence machine (CeRVIM) ainsi que du Centre de recherche en données massives (CRDM) de l’Université Laval. Il fait partie des regroupements stratégiques REPARTI et UNIQUE du Fonds de recherche du Québec – Nature et technologies (FRQNT), du centre VITAM du Fonds de recherche du Québec – Santé (FRQS) et de l’Observatoire international sur les impacts sociétaux de l’IA et du numérique (OBVIA).

Ses intérêts de recherche portent sur l’élaboration de méthodes pour l’apprentissage automatique et l’optimisation stochastique. En particulier, il se consacre aux réseaux de neurones profonds, à l’apprentissage et au transfert de représentations, au méta-apprentissage ainsi qu’à l’apprentissage multitâche. Il s’intéresse également aux approches d’optimisation basées sur des modèles probabilistes ainsi qu’aux algorithmes évolutionnaires, entre autres pour l’optimisation boîte noire et la programmation automatique. Une part importante de ses travaux porte également sur la mise en pratique de ces techniques dans des domaines comme la vision numérique, la microscopie, la santé, l’énergie et les transports.

Étudiants actuels

Frédéric Beaupré

Doctorat - Université Laval

Catherine Bouchard

Doctorat - Université Laval

Olivier Bussière

Maîtrise recherche - Université Laval

Sara Karami

Doctorat - Université Laval

Rose Nayoung Kwon

Doctorat - Université Laval

Benjamin Léger

Doctorat - Université Laval

Samy Mammeri

Stagiaire de recherche - Université Laval

Doctorat - Université Laval

Doctorat - Université Laval

Site web

Adam Tupper

Doctorat - Université Laval

Site web

Publications

Robust Fine-Tuning from Non-Robust Pretrained Models: Mitigating Suboptimal Transfer With Epsilon-Scheduling

Ola Ahmad

Frédéric Precioso

Fine-tuning pretrained models is a standard and effective workflow in modern machine learning. However, robust fine-tuning (RFT), which aims… (voir plus) to simultaneously achieve adaptation to a downstream task and robustness to adversarial examples, remains challenging. Despite the abundance of non-robust pretrained models in open-source repositories, their potential for RFT is less understood. We address this knowledge gap by systematically examining RFT from such non-robust models. Our experiments reveal that fine-tuning non-robust models with a robust objective, even under small perturbations, can lead to poor performance, a phenomenon that we dub _suboptimal transfer_. In challenging scenarios (eg, difficult tasks, high perturbation), the resulting performance can be so low that it may be considered a transfer failure. We find that fine-tuning using a robust objective impedes task adaptation at the beginning of training and eventually prevents optimal transfer. However, we propose a novel heuristic, _Epsilon-Scheduling_, a schedule over perturbation strength used during training that promotes optimal transfer. Additionally, we introduce _expected robustness_, a metric that captures performance across a range of perturbations, providing a more comprehensive evaluation of the accuracy-robustness trade-off of diverse models at test-time. Extensive experiments on wide range of configurations (six pretrained models and five datasets) show that _Epsilon-Scheduling_ successfully prevents _suboptimal transfer_ and consistently improves expected robustness.

2025-12-31

International Conference on Learning Representations (Accept (Poster))

Personalized Federated Fine-Tuning of Vision Foundation Models for Healthcare

Adam Tupper

2025-09-30

arXiv (publié)

arxiv.org

A Guide to Robust Generalization: The Impact of Architecture, Pre-training, and Optimization Strategy

Ola Ahmad

Deep learning models operating in the image domain are vulnerable to small input perturbations. For years, robustness to such perturbations … (voir plus)was pursued by training models from scratch (i.e., with random initializations) using specialized loss objectives. Recently, robust fine-tuning has emerged as a more efficient alternative: instead of training from scratch, pretrained models are adapted to maximize predictive performance and robustness. To conduct robust fine-tuning, practitioners design an optimization strategy that includes the model update protocol (e.g., full or partial) and the specialized loss objective. Additional design choices include the architecture type and size, and the pretrained representation. These design choices affect robust generalization, which is the model's ability to maintain performance when exposed to new and unseen perturbations at test time. Understanding how these design choices influence generalization remains an open question with significant practical implications. In response, we present an empirical study spanning 6 datasets, 40 pretrained architectures, 2 specialized losses, and 3 adaptation protocols, yielding 1,440 training configurations and 7,200 robustness measurements across five perturbation types. To our knowledge, this is the most diverse and comprehensive benchmark of robust fine-tuning to date. While attention-based architectures and robust pretrained representations are increasingly popular, we find that convolutional neural networks pretrained in a supervised manner on large datasets often perform best. Our analysis both confirms and challenges prior design assumptions, highlighting promising research directions and offering practical guidance.

2025-09-28

NeurIPS.cc/2025/Workshop/Reliable_ML (publié)

High-order Component Attribution via Kolmogorov-Arnold Networks

Samy Mammeri

Component attribution methods provide insight into how parts of deep learning models, such as convolutional filters and attention heads, inf… (voir plus)luence model predictions. Despite their successes, existing attribution approaches typically assume component effects are additive and independent, neglecting complex interactions among components. Capturing these relations between components is crucial for a better mechanistic understanding of these models. In this work, we improve component attribution (COAR) by replacing the linear counterfactual estimator with a Kolmogorov–Arnold Network (KAN) surrogate fitted to example‑wise perturbation–response data. Then, a symbolic approximation of the learned KAN lets us compute mixed partial derivatives that captures and makes explicit high‑order component interactions that linear methods are missing. These symbolic expressions facilitate future integration with formal verification methods, enabling richer counterfactual analyses of internal model behavior. Preliminary results on standard image classification models demonstrate that our approach improves the accuracy of predicted counterfactuals and enable extraction of higher-order component interactions compared to linear attribution methods.

2025-09-28

NeurIPS.cc/2025/Workshop/MechInterp (poster)

Robust Fine-Tuning from Non-Robust Pretrained Models: Mitigating Suboptimal Transfer With Epsilon-Scheduling

Maxime Heuillet

Sabyasachi Sahoo

Yann Batiste Pequignot

Frédéric Precioso

Fine-tuning pretrained models is the standard approach in current machine learning practice, but simultaneously achieving adversarial robust… (voir plus)ness to adversarial examples remains a challenge. Despite the abundance of non-robust pretrained models in open-source repositories, their use for Robust Fine-Tuning (RFT) remains understudied. This work aims to bridge this knowledge gap by systematically examining RFT from such models. Our experiments reveal that fine-tuning non-robust models with a robust objective, even under small perturbations, can lead to poor performance, a phenomenon that we dub \emph{suboptimal transfer}. In fact, we find that fine-tuning using a robust objective impedes task alignment at the beginning of training and eventually prevents optimal transfer. To promote optimal transfer, we propose \emph{Epsilon-Scheduling}, a simple heuristic scheduling over perturbation strength. Additionally, we introduce \emph{expected robustness}, a metric that measures performance across a range of perturbations. Experiments on six pretrained models and five datasets show that \emph{Epsilon-Scheduling} prevents \emph{suboptimal transfer} and consistently improves the expected robustness.

2025-09-28

NeurIPS.cc/2025/Workshop/Reliable_ML (publié)

Robust Fine-Tuning from Non-Robust Pretrained Models: Mitigating Suboptimal Transfer With Adversarial Scheduling

Maxime Heuillet

Sabyasachi Sahoo

Yann Batiste Pequignot

Ola Ahmad

Audrey Durand

Frédéric Precioso

Fine-tuning pretrained models is a standard and effective workflow in modern machine learning. However, robust fine-tuning (RFT), which aims… (voir plus) to simultaneously achieve adaptation to a downstream task and robustness to adversarial examples, remains challenging. Despite the abundance of non-robust pretrained models in open-source repositories, their potential for RFT is less understood. We address this knowledge gap by systematically examining RFT from such non-robust models. Our experiments reveal that fine-tuning non-robust models with a robust objective, even under small perturbations, can lead to poor performance, a phenomenon that we dub \emph{suboptimal transfer}. In challenging scenarios (eg, difficult tasks, high perturbation), the resulting performance can be so low that it may be considered a transfer failure. We find that fine-tuning using a robust objective impedes task adaptation at the beginning of training and eventually prevents optimal transfer. However, we propose a novel heuristic, \emph{Epsilon-Scheduling}, a schedule over perturbation strength used during training that promotes optimal transfer. Additionally, we introduce \emph{expected robustness}, a metric that captures performance across a range of perturbations, providing a more comprehensive evaluation of the accuracy-robustness trade-off for diverse models at test time. Extensive experiments on a wide range of configurations (six pretrained models and five datasets) show that \emph{Epsilon-Scheduling} successfully prevents \emph{suboptimal transfer} and consistently improves expected robustness.

2025-09-26

ArXiv (prépublication)

arxiv.org

Conditional Adversarial Random Forest for Synthetic Electronic Health Record Generation

Cynthia García Ybarra

2025-09-21

NeurIPS.cc/2025/Workshop/WiML (publié)

Enhancing STED Microscopy via Fluorescence Lifetime Unmixing and Filtering in Two-Species SPLIT-STED

Andréanne Deschênes

Antoine Ollier

Marie Lafontaine

Albert Michaud-Gagnon

Jeffrey-Gabriel Steavan Santiague

Anthony Bilodeau

Paul De Koninck

Flavie Lavoie-Cardinal

2025-07-17

bioRxiv (prépublication)

A Self-Supervised Foundation Model for Robust and Generalizable Representation Learning in STED Microscopy

Anthony Bilodeau

Frédéric Beaupré

Julia Chabbert

Kamylle Thériault

Andréanne Deschênes

Jean-Michel Bellavance

Koraly Lessard

Renaud Bernatchez

Paul De Koninck

Flavie Lavoie-Cardinal

Foundation Models (FMs) have dramatically increased the potential and power of deep learning algorithms through general capacities over a va… (voir plus)riety of tasks. The performance increase they offer is obtained without elaborated specific trainings for domains such as natural language processing and computer vision. However, their application in specialized fields like biomedical imaging and fluorescence microscopy remains difficult due to distribution shifts and the scarcity of high-quality annotated datasets. The high cost of data acquisition and the requirement for in-domain expertise further exacerbate this challenge in microscopy. To address this we introduce STED-FM, a foundation model specifically designed for super-resolution STimulated Emission Depletion (STED) microscopy. STED-FM leverages a Vision Transformer architecture trained at scale with Masked Autoencoding on a new dataset of nearly one million STED images. STED-FM learns expressive latent representations without requiring extensive annotations, yielding robust performance across diverse downstream microscopy image analysis tasks. Unsupervised experiments demonstrate the discriminative structure of its learned latent space. These representations can be leveraged for multiple downstream applications, including fully supervised classification and segmentation with reduced annotation requirements. Moreover, STED-FM representations enhance the performance of deep learning–based image denoising and improve the quality of images generated by diffusion models, enabling latent attribute manipulation for the data-driven discovery of subtle nanostructures and phenotypes, as well as algorithmic super-resolution. Moreover, its powerful structure retrieval capabilities are integrated into automated STED microscopy acquisition pipelines, paving the way for smart microscopy. In sum, we demonstrate that STED-FM lays a robust foundation for state-of-the-art algorithms across a wide array of tasks, establishing it as a highly valuable and scalable resource for researchers in super-resolution microscopy.

2025-06-05

bioRxiv (prépublication)

Fatemeh Nourilenjan Nokabadi

TrackPGD: Efficient Adversarial Attack using Object Binary Masks against Robust Transformer Trackers

Yann Batiste Pequignot

Jean-François Lalonde

Adversarial perturbations can deceive neural networks by adding small, imperceptible noise to the input. Recent object trackers with transfo… (voir plus)rmer backbones have shown strong performance on tracking datasets, but their adversarial robustness has not been thoroughly evaluated. While transformer trackers are resilient to black-box attacks, existing white-box adversarial attacks are not universally applicable against these new transformer trackers due to differences in backbone architecture. In this work, we introduce TrackPGD, a novel white-box attack that utilizes predicted object binary masks to target robust transformer trackers. Built upon the powerful segmentation attack SegPGD, our proposed TrackPGD effectively influences the decisions of transformer-based trackers. Our method addresses two primary challenges in adapting a segmentation attack for trackers: limited class numbers and extreme pixel class imbalance. TrackPGD uses the same number of iterations as other attack methods for tracker networks and produces competitive adversarial examples that mislead transformer and non-transformer trackers such as MixFormerM, OSTrackSTS, TransT-SEG, and RTS on datasets including VOT2022STS, DAVIS2016, UAV123, and GOT-10k.

2025-05-26

Proceedings of the Conference on Robots and Vision (publié)

A Layer Selection Approach to Test Time Adaptation

Sabyasachi Sahoo

Mostafa Elaraby

Yann Batiste Pequignot

Frédéric Precioso

Test Time Adaptation (TTA) addresses the problem of distribution shift by adapting a pretrained model to a new domain during inference. When… (voir plus) faced with challenging shifts, most methods collapse and perform worse than the original pretrained model. In this paper, we find that not all layers are equally receptive to the adaptation, and the layers with the most misaligned gradients often cause performance degradation. To address this, we propose GALA, a novel layer selection criterion to identify the most beneficial updates to perform during test time adaptation. This criterion can also filter out unreliable samples with noisy gradients. Its simplicity allows seamless integration with existing TTA loss functions, thereby preventing degradation and focusing adaptation on the most trainable layers. This approach also helps to regularize adaptation to preserve the pretrained features, which are crucial for handling unseen domains. Through extensive experiments, we demonstrate that the proposed layer selection framework improves the performance of existing TTA approaches across multiple datasets, domain shifts, model architectures, and TTA losses.

2025-04-10

Proceedings of the AAAI Conference on Artificial Intelligence (publié)

Revisiting Data Augmentation for Ultrasound Images

Adam Tupper

Data augmentation is a widely used and effective technique to improve the generalization performance of deep neural networks. Yet, despite o… (voir plus)ften facing limited data availability when working with medical images, it is frequently underutilized. This appears to come from a gap in our collective understanding of the efficacy of different augmentation techniques across different tasks and modalities. One modality where this is especially true is ultrasound imaging. This work addresses this gap by analyzing the effectiveness of different augmentation techniques at improving model performance across a wide range of ultrasound image analysis tasks. To achieve this, we introduce a new standardized benchmark of 14 ultrasound image classification and semantic segmentation tasks from 10 different sources and covering 11 body regions. Our results demonstrate that many of the augmentations commonly used for tasks on natural images are also effective on ultrasound images, even more so than augmentations developed specifically for ultrasound images in some cases. We also show that diverse augmentation using TrivialAugment, which is widely used for natural images, is also effective for ultrasound images. Moreover, our proposed methodology represents a structured approach for assessing various data augmentations that can be applied to other contexts and modalities.

2024-12-31

Trans. Mach. Learn. Res. (publié)