1 code implementation • 2 Nov 2024 • Ali Bahri, Moslem Yazdanpanah, Mehrdad Noori, Sahar Dastani Oghani, Milad Cheraghalikhani, David Osowiech, Farzad Beizaee, Gustavo adolfo. vargas-hakim, Ismail Ben Ayed, Christian Desrosiers
Test-Time Adaptation (TTA) addresses distribution shifts during testing by adapting a pretrained model without access to source data.
1 code implementation • 8 Oct 2024 • Yihang Wu, Christian Desrosiers, Ahmad Chaddad
Federated learning (FL) has emerged as a promising approach to medical image analysis that allows deep model training using decentralized data while ensuring data privacy.
no code implementations • 30 Sep 2024 • Mélanie Gaillochet, Christian Desrosiers, Hervé Lombaert
However, these models typically require user interaction through handcrafted prompts such as bounding boxes, which limits their deployment to downstream tasks.
1 code implementation • 4 Jul 2024 • Mehrdad Noori, Milad Cheraghalikhani, Ali Bahri, Gustavo Adolfo Vargas Hakim, David Osowiechi, Moslem Yazdanpanah, Ismail Ben Ayed, Christian Desrosiers
To address these challenges, we propose FDS, Feedback-guided Domain Synthesis, a novel strategy that employs diffusion models to synthesize novel, pseudo-domains by training a single model on all source domains and performing domain mixing based on learned features.
1 code implementation • 19 Jun 2024 • David Osowiechi, Mehrdad Noori, Gustavo Adolfo Vargas Hakim, Moslem Yazdanpanah, Ali Bahri, Milad Cheraghalikhani, Sahar Dastani, Farzad Beizaee, Ismail Ben Ayed, Christian Desrosiers
In response, we present Weight Average Test-Time Adaptation (WATT) of CLIP, a pioneering approach facilitating full test-time adaptation (TTA) of this VLM.
no code implementations • 20 May 2024 • Ali Bahri, Moslem Yazdanpanah, Mehrdad Noori, Milad Cheraghalikhani, Gustavo Adolfo Vargas Hakim, David Osowiechi, Farzad Beizaee, Ismail Ben Ayed, Christian Desrosiers
We introduce a pioneering approach to self-supervised learning for point clouds, employing a geometrically informed mask selection strategy called GeoMask3D (GM3D) to boost the efficiency of Masked Auto Encoders (MAE).
1 code implementation • 1 May 2024 • Gustavo Adolfo Vargas Hakim, David Osowiechi, Mehrdad Noori, Milad Cheraghalikhani, Ali Bahri, Moslem Yazdanpanah, Ismail Ben Ayed, Christian Desrosiers
In this study, we introduce CLIP Adaptation duRing Test-Time (CLIPArTT), a fully test-time adaptation (TTA) approach for CLIP, which involves automatic text prompts construction during inference for their use as text supervision.
1 code implementation • 12 Apr 2024 • David Osowiechi, Gustavo A. Vargas Hakim, Mehrdad Noori, Milad Cheraghalikhani, Ali Bahri, Moslem Yazdanpanah, Ismail Ben Ayed, Christian Desrosiers
Despite their exceptional performance in vision tasks, deep learning models often struggle when faced with domain shifts during testing.
no code implementations • 28 Feb 2024 • Koffi Kossi, Stephane Coulombe, Christian Desrosiers, Ghyslain Gagnon
In this paper, we developed a parametric model for estimating the perceived audiovisual quality in videoconference services.
1 code implementation • CVPR 2024 • David Osowiechi, Gustavo A. Vargas Hakim, Mehrdad Noori, Milad Cheraghalikhani, Ali Bahri, Moslem Yazdanpanah, Ismail Ben Ayed, Christian Desrosiers
Despite their exceptional performance in vision tasks deep learning models often struggle when faced with domain shifts during testing.
1 code implementation • ICCV 2023 • Gustavo A. Vargas Hakim, David Osowiechi, Mehrdad Noori, Milad Cheraghalikhani, Ismail Ben Ayed, Christian Desrosiers
Deep Learning models have shown remarkable performance in a broad range of vision tasks.
no code implementations • 11 Jul 2023 • Julien Nicolas, Florent Chiaroni, Imtiaz Ziko, Ola Ahmad, Christian Desrosiers, Jose Dolz
Despite the recent progress in incremental learning, addressing catastrophic forgetting under distributional drift is still an open and important problem.
no code implementations • 23 May 2023 • Bach Kim, Jose Dolz, Pierre-Marc Jodoin, Christian Desrosiers
Our system has two components: 1) a segmentation network on the server side which processes the image mixture, and 2) a segmentation unmixing network which recovers the correct segmentation map from the segmentation mixture.
1 code implementation • 15 May 2023 • Antoine Théberge, Christian Desrosiers, Maxime Descoteaux, Pierre-Marc Jodoin
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 curated reference streamlines.
1 code implementation • 28 Mar 2023 • Mehrdad Noori, Milad Cheraghalikhani, Ali Bahri, Gustavo A. Vargas Hakim, David Osowiechi, Ismail Ben Ayed, Christian Desrosiers
This paper presents a first Token-level Feature Stylization (TFS-ViT) approach for domain generalization, which improves the performance of ViTs to unseen data by synthesizing new domains.
1 code implementation • 27 Jan 2023 • Farzad Beizaee, Christian Desrosiers, Gregory A. Lodygensky, Jose Dolz
In this paper, we propose an unsupervised framework based on normalizing flows that harmonizes MR images to mimic the distribution of the source domain.
1 code implementation • 18 Jan 2023 • Mélanie Gaillochet, Christian Desrosiers, Hervé Lombaert
The performance of learning-based algorithms improves with the amount of labelled data used for training.
2 code implementations • 16 Jan 2023 • Mélanie Gaillochet, Christian Desrosiers, Hervé Lombaert
This paper proposes Test-time Augmentation for Active Learning (TAAL), a novel semi-supervised active learning approach for segmentation that exploits the uncertainty information offered by data transformations.
no code implementations • 7 Nov 2022 • Djebril Mekhazni, Maximilien Dufau, Christian Desrosiers, Marco Pedersoli, Eric Granger
In this scenario, the ReID model must adapt to a complex target domain defined by a network of diverse video cameras based on tracklet information.
1 code implementation • 20 Oct 2022 • David Osowiechi, Gustavo A. Vargas Hakim, Mehrdad Noori, Milad Cheraghalikhani, Ismail Ben Ayed, Christian Desrosiers
A major problem of deep neural networks for image classification is their vulnerability to domain changes at test-time.
no code implementations • 9 Jun 2022 • Ahmad Chaddad, Paul Daniel Mingli Zhang, Saima Rathore, Paul Sargos, Christian Desrosiers, Tamim Niazi
These results demonstrate the usefulness of proposed DRFs as non-invasive biomarker for predicting treatment response in patients with brain tumors.
no code implementations • 5 Jun 2022 • Ahmad Chaddad, Jiali Li, Qizong Lu, Yujie Li, Idowu Paul Okuwobi, Camel Tanougast, Christian Desrosiers, Tamim Niazi
With AI, new radiomic models using the deep learning techniques will be also described.
no code implementations • 4 Jun 2022 • Ahmad Chaddad, Lama Hassan, Christian Desrosiers
Our results suggest that the proposed GMM-CNN features could improve the prediction of COVID-19 in chest computed tomography and X-ray scans.
no code implementations • 4 Feb 2022 • Jizong Peng, Ping Wang, Marco Pedersoli, Christian Desrosiers
Unsupervised pre-training has been proven as an effective approach to boost various downstream tasks given limited labeled data.
no code implementations • CVPR 2022 • Moslem Yazdanpanah, Aamer Abdul Rahman, Muawiz Chaudhary, Christian Desrosiers, Mohammad Havaei, Eugene Belilovsky, Samira Ebrahimi Kahou
Batch Normalization is a staple of computer vision models, including those employed in few-shot learning.
no code implementations • 16 Nov 2021 • 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 with multiple prototypes.
2 code implementations • 21 Sep 2021 • Bingyuan Liu, Christian Desrosiers, Ismail Ben Ayed, Jose Dolz
Combined with a standard cross-entropy loss over the labeled pixels, our novel formulation integrates two important terms: (i) a Shannon entropy loss defined over the less-supervised images, which encourages confident student predictions in the bottom branch; and (ii) a KL divergence term, which transfers the knowledge (i. e., predictions) of the strongly supervised branch to the less-supervised branch and guides the entropy (student-confidence) term to avoid trivial solutions.
no code implementations • 9 Sep 2021 • Athanasios N. Nikolakopoulos, Xia Ning, Christian Desrosiers, George Karypis
Collaborative recommendation approaches based on nearest-neighbors are still highly popular today due to their simplicity, their efficiency, and their ability to produce accurate and personalized recommendations.
no code implementations • 9 Aug 2021 • Benoit Anctil-Robitaille, Antoine Théberge, Pierre-Marc Jodoin, Maxime Descoteaux, Christian Desrosiers, Hervé Lombaert
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 those of T1w images.
no code implementations • 12 Jul 2021 • Ping Wang, Jizong Peng, Marco Pedersoli, Yuanfeng Zhou, Caiming Zhang, Christian Desrosiers
Despite their outstanding accuracy, semi-supervised segmentation methods based on deep neural networks can still yield predictions that are considered anatomically impossible by clinicians, for instance, containing holes or disconnected regions.
1 code implementation • 11 Mar 2021 • Laurent Chauvin, Kuldeep Kumar, Christian Desrosiers, William Wells III, Matthew Toews
Our measure generalizes the Jaccard index to account for soft set equivalence (SSE) between keypoint elements, via an adaptive kernel framework modeling uncertainty in keypoint appearance and geometry.
1 code implementation • 8 Mar 2021 • Jizong Peng, Marco Pedersoli, Christian Desrosiers
In this method, we maximize the MI for intermediate feature embeddings that are taken from both the encoder and decoder of a segmentation network.
1 code implementation • 15 Dec 2020 • Jose Dolz, Christian Desrosiers, Ismail Ben Ayed
In conjunction with a standard cross-entropy over the labeled pixels, our novel formulation integrates two important terms: (i) a Shannon entropy loss defined over the less-supervised images, which encourages confident student predictions at the bottom branch; and (ii) a Kullback-Leibler (KL) divergence, which transfers the knowledge from the predictions generated by the strongly supervised branch to the less-supervised branch, and guides the entropy (student-confidence) term to avoid trivial solutions.
no code implementations • 25 Nov 2020 • Bach Ngoc Kim, Jose Dolz, Christian Desrosiers, Pierre-Marc Jodoin
Results show that the segmentation accuracy of our method is similar to a system trained on non-encoded images, while considerably reducing the ability to recover subject identity.
1 code implementation • 31 Oct 2020 • Ping Wang, Jizong Peng, Marco Pedersoli, Yuanfeng Zhou, Caiming Zhang, Christian Desrosiers
Moreover, to encourage predictions from different networks to be both consistent and confident, we enhance this generalized JSD loss with an uncertainty regularizer based on entropy.
1 code implementation • 13 Oct 2020 • Jie Mei, Christian Desrosiers, Johannes Frasnelli
Diagnosis of Parkinson's disease (PD) is commonly based on medical observations and assessment of clinical signs, including the characterization of a variety of motor symptoms.
1 code implementation • 29 Sep 2020 • Pierre-Luc Delisle, Benoit Anctil-Robitaille, Christian Desrosiers, Herve Lombaert
This paper proposes to revisit the conventional image normalization approach by instead learning a common normalizing function across multiple datasets.
no code implementations • 1 Apr 2020 • Benoit Anctil-Robitaille, Christian Desrosiers, Herve Lombaert
To ensure that the generated diffusion tensors lie on the SPD(3) manifold, we exploit the theoretical properties of the exponential and logarithm maps of the Log-Euclidean metric.
Image-to-Image Translation Vocal Bursts Intensity Prediction
no code implementations • 31 Mar 2020 • Karthik Gopinath, Christian Desrosiers, Herve Lombaert
The varying cortical geometry of the brain creates numerous challenges for its analysis.
no code implementations • 20 Mar 2020 • Xuan Li, Yuchen Lu, Christian Desrosiers, Xue Liu
In this paper, we study the problem of out-of-distribution detection in skin disease images.
no code implementations • MIDL 2019 • Jizong Peng, Marco Pedersoli, Christian Desrosiers
The scarcity of labeled data often limits the application of deep learning to medical image segmentation.
no code implementations • 2 Dec 2019 • Pierre-Luc Delisle, Benoit Anctil-Robitaille, Christian Desrosiers, Herve Lombaert
To solve this problem, we propose an adversarial normalization approach for image segmentation which learns common normalizing functions across multiple datasets while retaining image realism.
no code implementations • 22 Nov 2019 • Ran He, Karthik Gopinath, Christian Desrosiers, Herve Lombaert
Our alignment and graph processing method provides a fast analysis of brain surfaces.
no code implementations • 22 Nov 2019 • Karthik Gopinath, Christian Desrosiers, Herve Lombaert
This paper proposes a new learnable graph pooling method for processing multiple surface-valued data to output subject-based information.
no code implementations • 15 Nov 2019 • Ahmad Chaddad, Saima Rathore, Mingli Zhang, Christian Desrosiers, Tamim Niazi
This paper proposes to use deep radiomic features (DRFs) from a convolutional neural network (CNN) to model fine-grained texture signatures in the radiomic analysis of recurrent glioblastoma (rGBM).
no code implementations • 3 Oct 2019 • Jizong Peng, Christian Desrosiers, Marco Pedersoli
The second, named Invariant Information Clustering (IIC), maximizes the mutual information between the clustering of a sample and its geometrically transformed version.
no code implementations • 2 Oct 2019 • Xuan Li, Yuchen Lu, Peng Xu, Jizong Peng, Christian Desrosiers, Xue Liu
In this paper, we study the problem of image recognition with non-differentiable constraints.
no code implementations • 9 Sep 2019 • Bach Ngoc Kim, Jose Dolz, Pierre-Marc Jodoin, Christian Desrosiers
Our novel architecture is composed of three components: 1) an encoder network which removes identity-specific features from input medical images, 2) a discriminator network that attempts to identify the subject from the encoded images, 3) a medical image analysis network which analyzes the content of the encoded images (segmentation in our case).
1 code implementation • 30 Aug 2019 • Arnab Kumar Mondal, Aniket Agarwal, Jose Dolz, Christian Desrosiers
In this work, we study the problem of training deep networks for semantic image segmentation using only a fraction of annotated images, which may significantly reduce human annotation efforts.
no code implementations • 15 Aug 2019 • Jizong Peng, Hoel Kervadec, Jose Dolz, Ismail Ben Ayed, Marco Pedersoli, Christian Desrosiers
An efficient strategy for weakly-supervised segmentation is to impose constraints or regularization priors on target regions.
1 code implementation • 8 Apr 2019 • Hoel Kervadec, Jose Dolz, Jing Yuan, Christian Desrosiers, Eric Granger, Ismail Ben Ayed
While sub-optimality is not guaranteed for non-convex problems, this result shows that log-barrier extensions are a principled way to approximate Lagrangian optimization for constrained CNNs via implicit dual variables.
2 code implementations • 27 Mar 2019 • Jizong Peng, Guillermo Estrada, Marco Pedersoli, Christian Desrosiers
In this paper, we aim to improve the performance of semantic image segmentation in a semi-supervised setting in which training is effectuated with a reduced set of annotated images and additional non-annotated images.
5 code implementations • 17 Dec 2018 • Hoel Kervadec, Jihene Bouchtiba, Christian Desrosiers, Eric Granger, Jose Dolz, Ismail Ben Ayed
We propose a boundary loss, which takes the form of a distance metric on the space of contours, not regions.
Brain Lesion Segmentation From Mri Ischemic Stroke Lesion Segmentation +5
1 code implementation • 19 Nov 2018 • Jose Dolz, Christian Desrosiers, Ismail Ben Ayed
Despite the technological advances in medical imaging, IVD localization and segmentation are still manually performed, which is time-consuming and prone to errors.
1 code implementation • 29 Oct 2018 • Arnab Kumar Mondal, Jose Dolz, Christian Desrosiers
In addition, our work presents a comprehensive analysis of different GAN architectures for semi-supervised segmentation, showing recent techniques like feature matching to yield a higher performance than conventional adversarial training approaches.
no code implementations • 16 Oct 2018 • Jose Dolz, Ismail Ben Ayed, Christian Desrosiers
First, instead of combining the available image modalities at the input, each of them is processed in a different path to better exploit their unique information.
no code implementations • 28 May 2018 • Jose Dolz, Xiaopan Xu, Jerome Rony, Jing Yuan, Yang Liu, Eric Granger, Christian Desrosiers, Xi Zhang, Ismail Ben Ayed, Hongbing Lu
Precise segmentation of bladder walls and tumor regions is an essential step towards non-invasive identification of tumor stage and grade, which is critical for treatment decision and prognosis of patients with bladder cancer (BC).
no code implementations • 15 Apr 2018 • Kuldeep Kumar, Kaleem Siddiqi, Christian Desrosiers
Results highlight the ability of our method to group streamlines into plausible bundles and illustrate the impact of sparsity priors on the performance of the proposed methods.
3 code implementations • 9 Apr 2018 • Jose Dolz, Karthik Gopinath, Jing Yuan, Herve Lombaert, Christian Desrosiers, Ismail Ben Ayed
Therefore, the proposed network has total freedom to learn more complex combinations between the modalities, within and in-between all the levels of abstraction, which increases significantly the learning representation.
Ranked #1 on Medical Image Segmentation on iSEG 2017 Challenge
no code implementations • 27 Mar 2018 • Karthik Gopinath, Christian Desrosiers, Herve Lombaert
This paper presents a novel approach for learning and exploiting surface data directly across surface domains.
1 code implementation • 14 Dec 2017 • Jose Dolz, Christian Desrosiers, Li Wang, Jing Yuan, Dinggang Shen, Ismail Ben Ayed
We report evaluations of our method on the public data of the MICCAI iSEG-2017 Challenge on 6-month infant brain MRI segmentation, and show very competitive results among 21 teams, ranking first or second in most metrics.
Ranked #1 on Infant Brain Mri Segmentation on iSEG 2017 Challenge
no code implementations • 29 Nov 2017 • Ahmad Chaddad, Behnaz Naisiri, Marco Pedersoli, Eric Granger, Christian Desrosiers, Matthew Toews
This paper proposes a principled information theoretic analysis of classification for deep neural network structures, e. g. convolutional neural networks (CNN).
1 code implementation • 16 Oct 2017 • Jose Dolz, Ismail Ben Ayed, Jing Yuan, Christian Desrosiers
Neonatal brain segmentation in magnetic resonance (MR) is a challenging problem due to poor image quality and low contrast between white and gray matter regions.
no code implementations • 18 Sep 2017 • Kuldeep Kumar, Laurent Chauvin, Mathew Toews, Olivier Colliot, Christian Desrosiers
So far, fingerprinting studies have focused on identifying features from single-modality MRI data, which capture individual characteristics in terms of brain structure, function, or white matter microstructure.
no code implementations • 18 Sep 2017 • Kuldeep Kumar, Pietro Gori, Benjamin Charlier, Stanley Durrleman, Olivier Colliot, Christian Desrosiers
We use it to cluster fibers with a dictionary learning and sparse coding-based framework, and present a preliminary analysis using HCP data.
1 code implementation • 28 Apr 2017 • Jose Dolz, Ismail Ben Ayed, Christian Desrosiers
We propose to constrain segmentation functionals with a dimensionless, unbiased and position-independent shape compactness prior, which we solve efficiently with an alternating direction method of multipliers (ADMM).
no code implementations • 21 Apr 2017 • Tobias Fechter, Sonja Adebahr, Dimos Baltas, Ismail Ben Ayed, Christian Desrosiers, Jose Dolz
These figures translate into a very good agreement with the reference contours and an increase in accuracy compared to other methods.
no code implementations • CVPR 2017 • Jose Dolz, Ismail Ben Ayed, Christian Desrosiers
We formulate an Alternating Direction Method of Mul-tipliers (ADMM) that systematically distributes the computations of any technique for optimizing pairwise functions, including non-submodular potentials.