I
Issam H. Laradji
Researcher at McGill University
Publications - 10
Citations - 122
Issam H. Laradji is an academic researcher from McGill University. The author has contributed to research in topics: Computer science & Deep learning. The author has an hindex of 3, co-authored 10 publications receiving 49 citations. Previous affiliations of Issam H. Laradji include James Cook University.
Papers
More filters
Proceedings Article
Online Fast Adaptation and Knowledge Accumulation (OSAKA): a New Approach to Continual Learning
Massimo Caccia,Pau Rodríguez,Oleksiy Ostapenko,Fabrice Normandin,Min Lin,Lucas Page-Caccia,Issam H. Laradji,Irina Rish,Alexandre Lacoste,David Vazquez,Laurent Charlin +10 more
TL;DR: It is shown in an empirical study that ContinualMAML, an online extension of the popular MAML algorithm, is better suited to the new scenario than the aforementioned methodologies including standard continual learning and meta-learning approaches.
Posted Content
Counting Cows: Tracking Illegal Cattle Ranching From High-Resolution Satellite Imagery
Issam H. Laradji,Pau Rodríguez,Freddie Kalaitzis,David Vazquez,Ross Young,Ed Davey,Alexandre Lacoste +6 more
TL;DR: This work explores the feasibility of tracking and counting cattle at the continental scale from satellite imagery, and shows promising results and highlights important directions for the next steps on both counting algorithms and the data collection process for solving such challenges.
Posted Content
Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations
Pau Rodríguez,Massimo Caccia,Alexandre Lacoste,Lee Zamparo,Issam H. Laradji,Laurent Charlin,David Vazquez +6 more
TL;DR: In this paper, the authors propose a counterfactual method that learns a perturbation in a disentangled latent space that is constrained using a diversity-enforcing loss to uncover multiple valuable explanations about the model's prediction.
Posted Content
Affinity LCFCN: Learning to Segment Fish with Weak Supervision.
Issam H. Laradji,Alzayat Saleh,Pau Rodríguez,Derek Nowrouzezahrai,Mostafa Rahimi Azghadi,David Vazquez +5 more
TL;DR: This work proposes an automatic segmentation model efficiently trained on images labeled with only point-level supervision, where each fish is annotated with a single click, and shows that A-LCFCN achieves better segmentation results than LCFCN and a standard baseline.
Journal ArticleDOI
A Deep Learning Localization Method for Measuring Abdominal Muscle Dimensions in Ultrasound Images
Alzayat Saleh,Issam H. Laradji,Corey Lammie,David Vazquez,Carol Ann Flavell,Mostafa Rahimi Azghadi +5 more
TL;DR: In this paper, a modified Fully Convolutional Network (FCN) is used to generate blobs of coordinate locations of measurement endpoints, similar to what a human operator does.