no code implementations • 12 Oct 2021 • Francis Dutil, Alexandre See, Lisa Di Jorio, Florent Chandelier
In this technical report, we explore the use of homomorphic encryption (HE) in the context of training and predicting with deep learning (DL) models to deliver strict \textit{Privacy by Design} services, and to enforce a zero-trust model of data governance.
no code implementations • 20 Jul 2021 • Jonatan Reyes, Lisa Di Jorio, Cecile Low-Kam, Marta Kersten-Oertel
Our performance evaluations show 9% better predictions with MNIST, 18% with Fashion-MNIST, and 5% with CIFAR-10 in the non-IID setting.
no code implementations • 20 Oct 2020 • Tristan Sylvain, Francis Dutil, Tess Berthier, Lisa Di Jorio, Margaux Luck, Devon Hjelm, Yoshua Bengio
In hospitals, data are siloed to specific information systems that make the same information available under different modalities such as the different medical imaging exams the patient undergoes (CT scans, MRI, PET, Ultrasound, etc.)
no code implementations • 2 Jul 2020 • Farshid Varno, Lucas May Petry, Lisa Di Jorio, Stan Matwin
We empirically show that compared to prevailing fine-tuning practices, FAST learns the target task faster and forgets the source task slower.
no code implementations • ICCV 2019 • Qicheng Lao, Mohammad Havaei, Ahmad Pesaranghader, Francis Dutil, Lisa Di Jorio, Thomas Fevens
), and the style, which is usually not well described in the text (e. g., location, quantity, size, etc.).
no code implementations • 25 May 2019 • Farshid Varno, Behrouz Haji Soleimani, Marzie Saghayi, Lisa Di Jorio, Stan Matwin
Transferring knowledge from one neural network to another has been shown to be helpful for learning tasks with few training examples.
no code implementations • 28 Mar 2019 • Saeid Asgari Taghanaki, Mohammad Havaei, Tess Berthier, Francis Dutil, Lisa Di Jorio, Ghassan Hamarneh, Yoshua Bengio
The scarcity of richly annotated medical images is limiting supervised deep learning based solutions to medical image analysis tasks, such as localizing discriminatory radiomic disease signatures.
no code implementations • 16 Feb 2017 • Michal Drozdzal, Gabriel Chartrand, Eugene Vorontsov, Lisa Di Jorio, An Tang, Adriana Romero, Yoshua Bengio, Chris Pal, Samuel Kadoury
Moreover, when applying our 2D pipeline on a challenging 3D MRI prostate segmentation challenge we reach results that are competitive even when compared to 3D methods.