Marco Pedersoli
Department of System Engineering
Since February 2017 I am assistant professor at École de technologie supérieure (ETS), the youngest and fastest-growing university located in the center of Montreal, the AI Mountain!
In 2015-2016 I have been post-doc in THOTH at INRIA Grenoble with Dr. Cordelia Schmid and Dr. Jakob Verbeek. From 2012 to 2015 I was in VISICS at KU Leuven with prof. Tinne Tuytelaars. I obtained my Ph.D. at the Computer Vision Center and the Autonomous University of Barcelona (UAB) under the supervision of Jordi Gonzàlez and Juan José Villanueva. For more details check my CV.
Research interests:
- Information and Communications Technologies
Research areas:
- Neural networks
- Machine learning
- Computer vision
- Pattern recognition
- Convolutional Neural Networks
- Recurrent Neural Networks
- Weakly Supervised Learning
- Unsupervised Learning
- Efficient Learning
- Learning on embedded devices
SYS819: Apprentissage profond
+ Original articles in refereed journals and books chapters
«Shape-aware joint distribution alignment for cross-domain image segmentation»Wang, Ping, Peng, Jizong, Pedersoli, Marco, Zhou, Yuan-Feng, Zhang, Cai-Ming and Desrosiers, Christian.” |
«CAT: Constrained adversarial training for anatomically-plausible semi-supervised segmentation»Wang, Ping, Peng, Jizong, Pedersoli, Marco, Zhou, Yuan-Feng, Zhang, Cai-Ming and Desrosiers, Christian.” |
«Incremental multi-target domain adaptation for object detection with efficient domain transfer»Le Thanh Nguyen-Meidine, Madhu Kiran, Marco Pedersoli, Jose Dolz, Louis-Antoine Blais-Morin, Eric Granger” |
«Deep clustering: On the link between discriminative models and K-means»Mohammed Jabi, Marco Pedersoli, Amar Mitiche, Ismail Ben Ayed” |
«Self-paced and self-consistent co-training for semi-supervised image segmentation»Ping Wang, Jizong Peng, Marco Pedersoli, Yuanfeng Zhou, Caiming Zhang, Christian Desrosiers” |
Read More >
+ Papers in refereed conference proceedings
«Privileged knowledge distillation for dimensional emotion recognition in the wild»Aslam, Muhammad Haseeb, Osama Zeeshan, Muhammad, Pedersoli, Marco, Koerich, Alessandro L., Bacon, Simon and Granger, Eric.” |
«Cascaded zoom-in detector for high resolution aerial images»Meethal, Akhil, Granger, Eric and Pedersoli, Marco.” |
«Negative evidence matters in interpretable histology image classification»Belharbi, Soufiane, Pedersoli, Marco, Ben Ayed, Ismail, McCaffrey, Luke and Granger, Éric.” |
«OCR-VQGAN: Taming text-within-image generation»Rodriguez, Juan A., Vazquez, David, Laradji, Issam, Pedersoli, Marco and Rodriguez, Pau.” |
«Camera alignment and weighted contrastive learning for domain adaptation in video person ReID»Mekhazni, Djebril, Dufau, Maximilien, Desrosiers, Christian, Pedersoli, Marco and Granger, Eric.” |
+ Code
- Roi-Pooling in Lasagne. Porting of R-CNN roi-pooling in Lasagnegithub.
- Weakly Supervised Detection. Python (Caffe) Code based on Fast RCNN for weakly supervised detection github.
- Face detection evaluation code. Python and C source codebitbucket.
- Fast 3D Object Detection. Python and C source code github.
- Deformation Field Model. Python and C source code github.
Marco
Pedersoli
Research & Innovation
Contact Us
Pavillon Principal (A)
1100, rue Notre-Dame Ouest
Montréal, QC, H3C 1K3
Room A-3600
Tel.: +1 (514) 396-8650
E-Mail: eric.granger@etsmtl.ca