Unlocking the power of L1 regularization: A novel approach to taming overfitting in CNN for image classification

Sheikh, Ramla, Wahid, Fazli, Ali, Sikandar, Alkhayyat, Ahmed, Ma, YingLiang, Khan, Jawad and Lee, Youngmoon (2025) Unlocking the power of L1 regularization: A novel approach to taming overfitting in CNN for image classification. PLoS One, 20 (9). ISSN 1932-6203

Preview

PDF (journal.pone.0327985) - Published Version Available under License Creative Commons Attribution. Download (4MB) | Preview

Abstract

Convolutional Neural Networks (CNNs) stand as indispensable tools in deep learning, capable of autonomously extracting crucial features from diverse data types. However, the intricacies of CNN architectures can present challenges such as overfitting and underfitting, necessitating thoughtful strategies to optimize their performance. In this work, these issues have been resolved by introducing L1 regularization in the basic architecture of CNN when it is applied for image classification. The proposed model has been applied to three different datasets. It has been observed that incorporating L1 regularization with different coefficient values has distinct effects on the working mechanism of CNN architecture resulting in improving its performance. In MNIST digit classification, L1 regularization (coefficient: 0.01) simplifies feature representation and prevents overfitting, leading to enhanced accuracy. In the Mango Tree Leaves dataset, dual L1 regularization (coefficient: 0.001 for convolutional and 0.01 for dense layers) improves model interpretability and generalization, facilitating effective leaf classification. Additionally, for hand-drawn sketches like those in the Quick, Draw! Dataset, L1 regularization (coefficient: 0.001) refines feature representation, resulting in improved recognition accuracy and generalization across diverse sketch categories. These findings underscore the significance of regularization techniques like L1 regularization in fine-tuning CNNs, optimizing their performance, and ensuring their adaptability to new data while maintaining high accuracy. Such strategies play a pivotal role in advancing the utility of CNNs across various domains, further solidifying their position as a cornerstone of deep learning.

Item Type:	Article
Additional Information:	Data Availability: We used the following benchmark datasets, which are freely available online: • MNIST: Available at https://www.kaggle.com/datasets/oddrationale/mnist-in-csv • Mango Trees Leaf: Available at https://data.mendeley.com/datasets/94jf97jzc8/1 • Hand Drawn Sketches Images (Tree Category): Available at http://cybertron.cg.tuberlin.de/eitz/projects/classifysketch/ Paper code for replication will be available at https://github.com/hqsikandar/L1-REGULARIZATION-for-CNN. Funding information: This work was supported by Institute of Information and Communications Technology Planning and Evaluation (IITP) grant IITP-2025-RS-2020-II201741, RS-2022-00155885, RS-2024-00423071 funded by the Korea government (MSIT).
Faculty \ School:	Faculty of Science > School of Computing Sciences
UEA Research Groups:	Faculty of Science > Research Groups > Data Science and AI Faculty of Science > Research Groups > Norwich Epidemiology Centre Faculty of Medicine and Health Sciences > Research Groups > Norwich Epidemiology Centre Faculty of Science > Research Groups > Visual Computing and Signal Processing
Depositing User:	LivePure Connector
Date Deposited:	17 Sep 2025 16:30
Last Modified:	17 Sep 2025 19:30
URI:	https://ueaeprints.uea.ac.uk/id/eprint/100427
DOI:	10.1371/journal.pone.0327985

Downloads

Actions (login required)

View Item