Nader Asadi

I’m a computer science master’s student at Mila and Concordia University, advised by Eugene Belilovsky and Sudhir Mudur. I’m broadly interested in machine learning and computer vision. Currently, my research focuses on self-supervised learning, continual learning, and out-of-distribution generalization. I’m also interested in problems at the intersection of computer vision and language, particularly multi-modal video representation learning for video retrieval and summarization.

Also, I’m an enthusiastic developer in big data space, experienced in machine learning and data mining as well as design and development of data models, data warehouse and data lake solutions, and distributed data-processing/analytics systems.

News

May 12, 2022 I’m serving as a reviewer for TPAMI. 🕵️
Mar 2, 2022 Our paper got accepted to CVPR 2022! :tada:
Jan 20, 2022 Our paper got accepted to ICLR 2022! :tada:
Oct 23, 2021 One paper got accepted to NeurIPS 2021 workshop on Distribution Shifts.
Jan 1, 2021 Starting my MS at Mila and Concordia. :mortar_board:

Selected Papers

  1. CVPR
    Probing Representation Forgetting in Supervised and Unsupervised Continual Learning
    MohammadReza Davari*, Nader Asadi*, Sudhir Mudur, Rahaf Aljundi, and Eugene Belilovsky.
    IEEE/CVF Conference on Computer Vision and Pattern Recognition 2022
    arXiv
  2. ICLR
    New Insights on Reducing Abrupt Representation Change in Online Continual Learning
    Lucas Caccia, Rahaf Aljundi, Nader Asadi, Tinne Tuytelaars, Joelle Pineau, and Eugene Belilovsky.
    International Conference on Learning Representations 2022
    PDF Code
  3. Workshop
    Tackling Online One-Class Incremental Learning by Removing Negative Contrasts
    Nader Asadi, Sudhir Mudur, and Eugene Belilovsky.
    In NeurIPS 2021 Workshop on Distribution Shifts 2021
    PDF
  4. Preprint
    Towards shape biased unsupervised representation learning for domain generalization
    Nader Asadi, Amir M Sarfi, Mehrdad Hosseinzadeh, Zahra Karimpour, and Mahdi Eftekhari.
    arXiv preprint 2019
    arXiv