Rahaf Aljundi


I am interested in building machines that can keep learning (given any source of supervision), can tell when a novel input is provided and further point at instances that require annotation.
This includes the topics of continual learning ( incremental learning, lifelong learning), novelty detection ( out of distribution, anomaly detection), active learning and also domain adaptation.
I currently work at Toyota Motor Europe as a researcher in the Artificial intelligence team.
I have a PhD degree from KU Leuven university (Belgium) where I worked on the topic of continual learning under the supervision of prof. Tinne Tuytelaars.

News:

Selected Articles

2019

Online Continual Learning with Maximally Interfered Retrieval

Rahaf Aljundi*, Lucas Caccia*, Eugene Belilovsky*, Massimo Caccia*, Min Lin, Laurent Charlin, Tinne Tuytelaars in 2019 Conference on Neural Information Processing (NeurIPS'19).

Gradient based sample selection for online continual learning

Rahaf Aljundi, Min Lin, Baptiste Goujaud, Yoshua Bengio in 2019 Conference on Neural Information Processing (NeurIPS'19).

Task-Free Continual Learning

R Aljundi*, K Kelchtermans* and T Tuytelaars in Computer Vision and Pattern Recognition, 2019 (CVPR'19).

Selfless Sequential Learning

R Aljundi, M Rohrbach and T Tuytelaars in International Conference on Learning Representations, 2019 (ICLR'19).

2018

Memory Aware Synapses: Learning what (not) to forget

R Aljundi, F Babiloni, M Elhoseiny, M Rohrbach and T Tuytelaars in European Conference on Computer Vision, 2018 (ECCV'18).

2017

Continual Learning with Hebbian Synapses

R Aljundi and T Tuytelaars in Continuous and Open-Set Learning workshop (CVPR 2017).

Encoder Based Lifelong Learning

AR Triki*, R Aljundi*, MB Blaschko and T Tuytelaars in International Conference on Computer Vision, 2017 (ICCV'18)

Expert Gate: Lifelong Learning with a Network of Experts

R Aljundi, P Chakravarty, T Tuytelaars in Computer Vision and Pattern Recognition, 2017 (CVPR'17).

2016

Who’s that Actor? Automatic Labelling of Actors in TV series starting from IMDB Images

R Aljundi*, P Chakravarty*, T Tuytelaars in Asian Conference on Computer Vision, 2016 (ACCV'16).

Lightweight Unsupervised Domain Adaptation by Convolutional Filter Reconstruction

R Aljundi, T Tuytelaars in ECCV'16 workshop, TASK-CV: Transferring and Adapting Source Knowledge in Computer Vision

2015

Transfer Learning for Prostate Cancer Mapping Based on Multicentric MR imaging databases

R Aljundi, J Lehaire, F Prost-Boucle, O Rouviere, C Lartizien in

Landmarks-based kernelized subspace alignment for unsupervised domain adaptation

R Aljundi, R Emonet, D Muselet, M Sebban in Computer Vision and Pattern Recognition, 2015 (CVPR'15).

Education

  • KU Leuven Belgium
    PhD degree KU Leuven Belgium Thesis Continual learning in Neural Networks.
  • Jean Monnet (France), Uni. Alicante(Spain).
    MLDM: Masters in Machine Learning and Data Mining Uni. Jean Monnet (France), Uni. Alicante(Spain).
  • Damascus University
    (Syria) Computer Science Engineering: Artificial Intelligence Dept.

Work Experience

  • Jan 2020 - Present
    AI Researcher at Toyota Motor Europe, Artificial intelligence department.

  • Nov 2018- Feb 2021
    Research Intern at MILA, Topic: online continual learning.

  • Feb 2012 – Jun 2018
    Teacher Assistant; Pattern Recognition and Image Interpretation M.Sc. course, KU Leuven.

  • Feb 2015- Jul 2015
    Research Intern at CREATIS Lab, INSA Topic: Transfer Learning for Prostate Cancer Mapping Based on Multicentric MR imaging databases.

  • April 2014- Jun 2014
    Research Intern LAHC Lab Unsupervised visual domain adaptation.

  • Sep 2012 – Sep 2013
    Teacher Assistant; Intelligent search algorithms, 4th year B.Sc. course, Damascus University.

  • Nov 2010 – Jul 2013
    Software engineer at SOFTNET company for software solutions.

Awards

  • June 2018
    FWO PhD fellowship (renewal) for fundamental research.

  • June 2016
    The winner reading group, ICVSS 2016 summer school.

  • April 2016
    FWO PhD fellowship for fundamental research.

  • May 2014
    2nd place at ImageCLEF Domain Adaptation challeng.

  • July 2011
    3rd position in Fikra Competition for innovative ideas provided by ICT incubator for my B.Sc. graduation project "Online Human Tracking System".

Get in touch

Made with by Jemnou