2026-06-29T09:34:09Zhttps://docta.ucm.es/rest/oai/request

oai:docta.ucm.es:20.500.14352/1222862025-07-08T00:16:57Zcom_20.500.14352_14col_20.500.14352_20

Preserving the essential features in CNNs: pruning and analysis López González, Clara Isabel Gómez-Silva, María J. Besada Portas, Eva Pajares, Gonzalo 004.8 004.85 004.932 004.032.26 Convolutional Neural Networks Explainable Artificial Intelligence Compression Methods Factor Analysis Inteligencia artificial (Informática) 1203.17 Informática © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2024 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. Comunidad de Madrid Ministerio de Ciencia e Innovación (España) European Comission Depto. de Ingeniería de Software e Inteligencia Artificial (ISIA) Sección Deptal. de Arquitectura de Computadores y Automática (Físicas) Fac. de Ciencias Físicas TRUE pub 2025-07-07T17:12:34Z 2025-07-07T17:12:34Z 2024-06 conference paper VoR https://hdl.handle.net/20.500.14352/122286 0302-9743 10.1007/978-3-031-62799-6_14 1611-3349 eng Y2020/TCS-6420/IA-GES-BLOOM-CM/Hacia un sistema Integral para la Alerta y Gestión de BLOOMs de cianobacterias en aguas continentales info:eu-repo/grantAgreement/AEI/lPlan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023/TED2021-130123B-I00/ES/Más allá del uso de tecnologías digitales en blooms de cianobacterias: gestión inteligente de cianobacterias mediante el uso de gemelos digitales y computación en el borde/SMART-BLOOMS info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023/PID2021-127648OB-C33/ES/COOPERACION DE VEHICULOS DE SUPERFICIE Y AEREOS PARA APLICACIONES DE INSPECCION EN ENTORNOS CAMBIANTES/ 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 restricted access application/pdf