Enhancing Convolutional Neural Network Robustness Against Image Noise via an Artificial Visual System

Bin Li, Yuki Todo (), Sichen Tao (), Cheng Tang and Yu Wang
Additional contact information
Bin Li: Division of Electrical Engineering and Computer Science, Kanazawa University, Kanazawa 920-1192, Japan
Yuki Todo: Faculty of Electrical, Information and Communication Engineering, Kanazawa University, Kanazawa 920-1192, Japan
Sichen Tao: Faculty of Engineering, Toyama University, Gofuku, Toyama 930-8555, Japan
Cheng Tang: Faculty of Information Science and Electrical Engineering, Kyushu University, Fukuoka 819-0395, Japan
Yu Wang: Division of Electrical Engineering and Computer Science, Kanazawa University, Kanazawa 920-1192, Japan

Mathematics, 2025, vol. 13, issue 1, 1-19

Abstract: The convolutional neural network (CNN) was initially inspired by the physiological visual system, and its structure has become increasingly complex after decades of development. Although CNN architectures now have diverged from biological structures, we believe that the mechanism of feature extraction in the visual system can still provide valuable insights for enhancing CNN robustness and stability. In this study, we investigate the mechanism of neuron orientation selectivity and develop an artificial visual system (AVS) referring to the structure of the primary visual system. Through learning on an artificial object orientation dataset, AVS acquires orientation extraction capabilities. Subsequently, we employ the pre-trained AVS as an information pre-processing block at the front of CNNs to regulate their preference for different image features during training. We conducted a comprehensive evaluation of the AVS–CNN framework across different image tasks. Extensive results demonstrated that the CNNs enhanced by AVS exhibit significant model stability enhancement and error rate decrease on noise data. We propose that incorporating biological structures into CNN design still holds great potential for improving overall performance.

Keywords: CNN; robustness; artificial visual system (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2025
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/13/1/142/pdf (application/pdf)
https://www.mdpi.com/2227-7390/13/1/142/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:13:y:2025:i:1:p:142-:d:1558857

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().