Search Results for author:
Found 1 papers, 0 papers with code
ImpressLearn: Continual Learning via Combined Task Impressions
Starting from existing work on network masking (Wortsman et al., 2020), we show that simply learning a linear combination of a small number of task-specific supermasks (impressions) on a randomly initialized backbone network is sufficient to both retain accuracy on previously learned tasks, as well as achieve high accuracy on unseen tasks.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
