Preserving the essential features in CNNs: pruning and analysis
Loading...
Official URL
Full text at PDC
Publication date
2024
Advisors (or tutors)
Editors
Journal Title
Journal ISSN
Volume Title
Publisher
Citation
López-González, C.I., Gómez-Silva, M.J., Besada-Portas, E., Pajares, G. (2024). Preserving the Essential Features in CNNs: Pruning and Analysis. In: Alonso-Betanzos, A., et al. Advances in Artificial Intelligence. CAEPIA 2024. Lecture Notes in Computer Science(), vol 14640. Springer, Cham. https://doi.org/10.1007/978-3-031-62799-6_14
Abstract
The exceptional performance of Convolutional Neural Networks (CNNs) entails increasing requirements in computing power and storage. While several efficient compression methods have been developed, there is no consideration on which features are removed or preserved, which can affect pruning. In this paper, we propose a novel filter pruning strategy, named Layer Factor Analysis one to one (LFA1-1), that, relying on explainability, selects the filters that best retain the essential features underlying convolutional layers. We provide insights about the relevance of preserving these features and verify its relationship with compressed network’s performance. The explanatory analysis carried out allows us to justify pruning efficiency and detect problematic parts. Experiments with VGG-16 on CIFAR-10 are conducted in order to validate our approach. Quantitative and qualitative comparisons with methods in the literature uncover pruning properties and prove the effectiveness of our proposal, which reaches a 89.1% parameters and 83.8% FLOPs reduction with the lowest accuracy drop.
Description
© The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2024