User-Defined Budget

Do you want to know more about pruning models for multiple domains according to a user budget? Check our paper “Budget-Aware Pruning: Handling Multiple Domains with Less Parameters”, just published in the Pattern Recognition journal.

In this paper, we addressed the multi-domain learning problem. We propose to prune a single model for multiple domains, making it more compact and efficient. To do so, we encourage multiple domains to share convolutional filters, enabling us to prune weights not used by any of the domains at test time.