527 citations · 1.5k across the 52 of their papers we have counts for
57 papers
LiSA: Linear Stochastic Attention for Long-Range Visual Modeling
Sahar Dastani, Fereshteh Shakeri, Samuel Barbeau +4
Self-attention has become the standard for modern sequence modeling, enabling Transformers to model long-range dependencies across a wide range of modalities. Despite these advance…
MoP-CLIP: A Mixture of Prompt-Tuned CLIP Models for Domain Incremental Learning
Julien Nicolas, Florent Chiaroni, Imtiaz Ziko +3
Despite the recent progress in incremental learning, addressing catastrophic forgetting under distributional drift is still an open and important problem. Indeed, while state-of-th…
Mixup-Privacy: A simple yet effective approach for privacy-preserving segmentation
Bach Kim, Jose Dolz, Pierre-Marc Jodoin +1
Privacy protection in medical data is a legitimate obstacle for centralized machine learning applications. Here, we propose a client-server image segmentation system which allows f…
What Matters in Reinforcement Learning for Tractography
Antoine Théberge, Christian Desrosiers, Maxime Descoteaux +1
Recently, deep reinforcement learning (RL) has been proposed to learn the tractography procedure and train agents to reconstruct the structure of the white matter without manually…
TFS-ViT: Token-Level Feature Stylization for Domain Generalization
Mehrdad Noori, Milad Cheraghalikhani, Ali Bahri +4
Standard deep learning models such as convolutional neural networks (CNNs) lack the ability of generalizing to domains which have not been seen during training. This problem is mai…
Harmonizing Flows: Unsupervised MR harmonization based on normalizing flows
Farzad Beizaee, Christian Desrosiers, Gregory A. Lodygensky +1
In this paper, we propose an unsupervised framework based on normalizing flows that harmonizes MR images to mimic the distribution of the source domain. The proposed framework cons…
TAAL: Test-time Augmentation for Active Learning in Medical Image Segmentation
Mélanie Gaillochet, Christian Desrosiers, Hervé Lombaert
Deep learning methods typically depend on the availability of labeled data, which is expensive and time-consuming to obtain. Active learning addresses such effort by prioritizing w…
Active learning for medical image segmentation with stochastic batches
Mélanie Gaillochet, Christian Desrosiers, Hervé Lombaert
The performance of learning-based algorithms improves with the amount of labelled data used for training. Yet, manually annotating data is particularly difficult for medical image…
Camera Alignment and Weighted Contrastive Learning for Domain Adaptation in Video Person ReID
Djebril Mekhazni, Maximilien Dufau, Christian Desrosiers +2
Systems for person re-identification (ReID) can achieve a high accuracy when trained on large fully-labeled image datasets. However, the domain shift typically associated with dive…
TTTFlow: Unsupervised Test-Time Training with Normalizing Flow
David Osowiechi, Gustavo A. Vargas Hakim, Mehrdad Noori +3
A major problem of deep neural networks for image classification is their vulnerability to domain changes at test-time. Recent methods have proposed to address this problem with te…
Deep radiomic signature with immune cell markers predicts the survival of glioma patients
Ahmad Chaddad, Paul Daniel Mingli Zhang, Saima Rathore +3
Imaging biomarkers offer a non-invasive way to predict the response of immunotherapy prior to treatment. In this work, we propose a novel type of deep radiomic features (DRFs) comp…
Can autism be diagnosed with AI?
Ahmad Chaddad, Jiali li, Qizong Lu +5
Radiomics with deep learning models have become popular in computer-aided diagnosis and have outperformed human experts on many clinical tasks. Specifically, radiomic models based…
Deep Radiomic Analysis for Predicting Coronavirus Disease 2019 in Computerized Tomography and X-ray Images
Ahmad Chaddad, Lama Hassan, Christian Desrosiers
This paper proposes to encode the distribution of features learned from a convolutional neural network using a Gaussian Mixture Model. These parametric features, called GMM-CNN, ar…
Boundary-aware Information Maximization for Self-supervised Medical Image Segmentation
Jizong Peng, Ping Wang, Marco Pedersoli +1
Unsupervised pre-training has been proven as an effective approach to boost various downstream tasks given limited labeled data. Among various methods, contrastive learning learns…
Diversified Multi-prototype Representation for Semi-supervised Segmentation
Jizong Peng, Christian Desrosiers, Marco Pedersoli
This work considers semi-supervised segmentation as a dense prediction problem based on prototype vector correlation and proposes a simple way to represent each segmentation class…
Trust your neighbors: A comprehensive survey of neighborhood-based methods for recommender systems
Athanasios N. Nikolakopoulos, Xia Ning, Christian Desrosiers +1
Collaborative recommendation approaches based on nearest-neighbors are still highly popular today due to their simplicity, their efficiency, and their ability to produce accurate a…
Segmentation with mixed supervision: Confidence maximization helps knowledge distillation
Bingyuan Liu, Christian Desrosiers, Ismail Ben Ayed +1
Despite achieving promising results in a breadth of medical image segmentation tasks, deep neural networks require large training datasets with pixel-wise annotations. Obtaining th…
Manifold-aware Synthesis of High-resolution Diffusion from Structural Imaging
Benoit Anctil-Robitaille, Antoine Théberge, Pierre-Marc Jodoin +3
The physical and clinical constraints surrounding diffusion-weighted imaging (DWI) often limit the spatial resolution of the produced images to voxels up to 8 times larger than tho…
Context-aware virtual adversarial training for anatomically-plausible segmentation
Ping Wang, Jizong Peng, Marco Pedersoli +3
Despite their outstanding accuracy, semi-supervised segmentation methods based on deep neural networks can still yield predictions that are considered anatomically impossible by cl…
Efficient Pairwise Neuroimage Analysis using the Soft Jaccard Index and 3D Keypoint Sets
Laurent Chauvin, Kuldeep Kumar, Christian Desrosiers +2
We propose a novel pairwise distance measure between image keypoint sets, for the purpose of large-scale medical image indexing. Our measure generalizes the Jaccard index to accoun…
Boosting Semi-supervised Image Segmentation with Global and Local Mutual Information Regularization
Jizong Peng, Marco Pedersoli, Christian Desrosiers
The scarcity of labeled data often impedes the application of deep learning to the segmentation of medical images. Semi-supervised learning seeks to overcome this limitation by exp…
Teach me to segment with mixed supervision: Confident students become masters
Jose Dolz, Christian Desrosiers, Ismail Ben Ayed
Deep segmentation neural networks require large training datasets with pixel-wise segmentations, which are expensive to obtain in practice. Mixed supervision could mitigate this di…
Privacy Preserving for Medical Image Analysis via Non-Linear Deformation Proxy
Bach Ngoc Kim, Jose Dolz, Christian Desrosiers +1
We propose a client-server system which allows for the analysis of multi-centric medical images while preserving patient identity. In our approach, the client protects the patient…
Self-paced and self-consistent co-training for semi-supervised image segmentation
Ping Wang, Jizong Peng, Marco Pedersoli +3
Deep co-training has recently been proposed as an effective approach for image segmentation when annotated data is scarce. In this paper, we improve existing approaches for semi-su…