1 code implementation • 22 May 2024 • Prashant Bhat, Bharath Renjith, Elahe Arani, Bahram Zonooz
Continual learning (CL) remains a significant challenge for deep neural networks, as it is prone to forgetting previously acquired knowledge.
1 code implementation • 28 Apr 2024 • Prashant Bhat, Bharath Renjith, Elahe Arani, Bahram Zonooz
To further leverage the global relationship between representations learned using CRL, we propose a regularization strategy to guide the classifier toward the activation correlations in the unit hypersphere of the CRL.