Incremental Learning

Learning from a stream of data without forgetting is important for lifelong learning systems. In this project, we study the incremental learning problem for a classification model, develop evaluation metrics and discuss strategies to mitigate catastrophic forgetting.

Continual Learning with Tiny Episodic Memories.
Arslan Chaudhry, Marcus Rohrbach, Mohamed Elhoseiny, Thalaiyasingam Ajanthan, Puneet K. Dokania, Philip H.S. Torr, and Marc’Aurelio Ranzato.
ICML Workshop: Multi-Task and Lifelong Reinforcement Learning, June 2019.
[pdf] [arxiv] [bib]

@article{Chaudhry_tinyer_icml2019,
  title={Continual Learning with Tiny Episodic Memories},
  author={Chaudhry, Arslan and Rohrbach, Marcus and Elhoseiny, Mohamed and Ajanthan, Thalaiyasingam and Dokania, Puneet K and Torr, Philip HS and Ranzato, Marc'Aurelio},
  journal={ICML Workshop: Multi-Task and Lifelong Reinforcement Learning},
  year={2019}
}

Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence.
Arslan Chaudhry*, Puneet K. Dokania*, Thalaiyasingam Ajanthan*, and Philip H.S. Torr.
European Conference on Computer Vision (ECCV), September 2018.
[pdf] [supp] [arxiv] [poster] [talk] [bib]

@article{chaudhry_rwalk_eccv2018,
  title={Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence},
  author={Chaudhry, Arslan and Dokania, Puneet K and Ajanthan, Thalaiyasingam and Torr, Philip HS},
  journal={ECCV},
  year={2018}
}