Budget-Aware Pruning for Multi-Domain Learning

Abstract

Deep learning has achieved state-of-the-art performance on several computer vision tasks and domains. Nevertheless, it still has a high computational cost and demands a significant amount of parameters. Such requirements hinder the use in resource-limited environments and demand both software and hardware optimization. Another limitation is that deep models are usually specialized into a single domain or task, requiring them to learn and store new parameters for each new one. Multi-Domain Learning (MDL) attempts to solve this problem by learning a single model that is capable of performing well in multiple domains. Nevertheless, the models are usually larger than the baseline for a single domain. This work tackles both of these problems: our objective is to prune models capable of handling multiple domains according to a user defined budget, making them more computationally affordable while keeping a similar classification performance. We achieve this by encouraging all domains to use a similar subset of filters from the baseline model, up to the amount defined by the user’s budget. Then, filters that are not used by any domain are pruned from the network. The proposed approach innovates by better adapting to resource-limited devices while, to our knowledge, being the only work that is capable of handling multiple domains at test time with fewer parameters and lower computational complexity than the baseline model for a single domain.

Publication
International Conference on Image Analysis Processing, ICIAP 2023, Udine, Italy, September 11-15, 2023
Samuel Felipe dos Santos
Samuel Felipe dos Santos
Post-Doc

My research interests include computer vision, deep learning, information retrieval, and machine learning.

Jurandy Almeida
Jurandy Almeida
Professor of Computer Science

My research interests are mainly in the areas of computer vision, deep learning, image processing, information retrieval, machine learning, and pattern recognition.