Hi!
My name is Soufiane Belharbi. I am a post-doc at LIVIA Lab., ÉTS, Montreal in collaboration with McCaffrey Lab. / GCRC McGill. I am working with Eric Granger, Ismail Ben Ayed, and Luke McCaffrey on training neural networks with weak supervision.
Research Interests
- Machine learning
- Neural networks
- Representation learning
- Weakly supervised learning
- Interpretable machine learning
News
New challenge @ 8TH ABAW @ CVPR 2025. Ambivalence/Hesitancy (AH) Recognition Challenge at 8th Workshop and Competition on Affective & Behavior Analysis in-the-wild (ABAW). [Page][Results][White paper]
- Apr. 2025: FG 2025, “Disentangled Source-Free Personalization for Facial Expression Recognition with Neutral Target Data”. [arXiv][Code]
- Apr. 2025: MIDL 2025, “PixelCAM: Pixel Class Activation Mapping for Histology Image Classification and ROI Localization”. [arXiv][Code]
- Mar. 2025: “Advancements in Affective and Behavior Analysis: The 8th ABAW Workshop and Competition”. [White paper]
- Jan. 2025: New arXiv, “TeD-Loc: Text Distillation for Weakly Supervised Object Localization”. [arXiv][Code][Page]
- Jan. 2025: New challenge is now open @ 8TH ABAW @ CVPR 2025. “Ambivalence/Hesitancy (AH) Recognition Challenge at 8th Workshop and Competition on Affective & Behavior Analysis in-the-wild (ABAW)”. [Page][Results][White paper]
- Jan. 2025: Pattern Recognition journal, “CoLo-CAM: Class Activation Mapping for Object Co-Localization in Weakly-Labeled Unconstrained Videos”. [arXiv][Code][Page][Free journal access until March 14, 2025]
- Oct. 2024: WACV 2025, “A Realistic Protocol for Evaluation of Weakly Supervised Object Localization”. [arXiv][Code]
Phd
I completed my PhD in computer science at the Institut National des Sciences Appliquées de Rouen Normandie (INSA Rouen Normandie) in LITIS lab, Apprentissage (Learning) team (Oct. 2014-Jul.2018). I was supervised by Prof. Sébastien Adam (director), Clément Chatelain, and Romain Hérault. During my PhD, I conducted research on the regularization of neural networks through representation learning with particular focus on learning scenarios where only few training samples are available. [BibTeX] [ArXiv][HAL-Thèse][Presentation]
@phdthesis{sbelharbiphd2018, author = {Belharbi, S.}, title = {Neural Networks Regularization Through Representation Learning}, school = {Normandie Université, INSA Rouen Normandie, LITIS laboratory}, year = {2018}, pages = {196}, note = {Supervisor: Sébastien Adam, Advisors: Clément Chatelain, Romain Hérault}, url = {https://arxiv.org/pdf/1807.05292} }