Conference paper · 2025 · Open access

CNN Architecture Assessment: Exploring Depth, Width, and Kernel Size for Image Classification

Eduardo Buss, Érick Radmann, Ruhan Conceição, Bruno Zatt, Luciano Volcan Agostini

Escola Regional de Aprendizado de Máquina e Inteligência Artificial da Região Sul (ERAMIA-RS), 424–427 · Published 12 November 2025 · DOI 10.5753/eramiars.2025.16782

Open PDFView at the publisherCite this paper

In brief

“CNN Architecture Assessment: Exploring Depth, Width, and Kernel Size for Image Classification” is a 2025 conference paper by Eduardo Buss and 4 co-authors, published in Escola Regional de Aprendizado de Máquina e Inteligência Artificial da Região Sul (ERAMIA-RS). OpenAlex counts 1 citations as of 18 November 2026. It is open access: the full text is free to read at Escola Regional de Aprendizado de Máquina e Inteligência Artificial da Região Sul (ERAMIA-RS).

Citations
1
Most cited in
2026 (1)
Field-weighted impact
0.20
References
6
Authors
5

Abstract

This paper investigates the impact of different convolutional neural network (CNN) architectures on image classification performance using the CIFAR-10 dataset. We evaluate variations in the number of convolutional layers, kernel size, and number of filters. Experiments indicate that increasing the number of filters and slightly enlarging kernel size generally improves accuracy, while deeper models do not always yield better results. The CIFAR-10 dataset contains 60,000 color images across 10 classes, with 45,000 for training, 5,000 for validation, and 10,000 for final testing.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Buss, E., Radmann, É., Conceição, R., Zatt, B., & Agostini, L. V. (2025). CNN Architecture Assessment: Exploring Depth, Width, and Kernel Size for Image Classification. Escola Regional de Aprendizado de Máquina e Inteligência Artificial da Região Sul (ERAMIA-RS), 424–427. https://doi.org/10.5753/eramiars.2025.16782

MLA 9

Buss, Eduardo, et al. “CNN Architecture Assessment: Exploring Depth, Width, and Kernel Size for Image Classification.” Escola Regional de Aprendizado de Máquina e Inteligência Artificial da Região Sul (ERAMIA-RS), 2025, pp. 424–427. https://doi.org/10.5753/eramiars.2025.16782.

Chicago

Buss, Eduardo, Érick Radmann, Ruhan Conceição, Bruno Zatt, and Luciano Volcan Agostini. 2025. “CNN Architecture Assessment: Exploring Depth, Width, and Kernel Size for Image Classification.” Escola Regional de Aprendizado de Máquina e Inteligência Artificial da Região Sul (ERAMIA-RS): 424–427. https://doi.org/10.5753/eramiars.2025.16782.

Harvard

Buss, E. et al. (2025) ‘CNN Architecture Assessment: Exploring Depth, Width, and Kernel Size for Image Classification’, Escola Regional de Aprendizado de Máquina e Inteligência Artificial da Região Sul (ERAMIA-RS), pp. 424–427. doi:10.5753/eramiars.2025.16782.

IEEE

E. Buss, É. Radmann, R. Conceição, B. Zatt, and L. V. Agostini, “CNN Architecture Assessment: Exploring Depth, Width, and Kernel Size for Image Classification,” Escola Regional de Aprendizado de Máquina e Inteligência Artificial da Região Sul (ERAMIA-RS), pp. 424–427, 2025, doi: 10.5753/eramiars.2025.16782.

BibTeX

@inproceedings{buss2025architecture,
  title     = {{CNN Architecture Assessment: Exploring Depth, Width, and Kernel Size for Image Classification}},
  author    = {Buss, Eduardo and Radmann, Érick and Conceição, Ruhan and Zatt, Bruno and Agostini, Luciano Volcan},
  booktitle = {Escola Regional de Aprendizado de Máquina e Inteligência Artificial da Região Sul (ERAMIA-RS)},
  year      = {2025},
  pages     = {424--427},
  doi       = {10.5753/eramiars.2025.16782},
  url       = {https://doi.org/10.5753/eramiars.2025.16782}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications

  • convolutional neural network architecture
  • network depth
  • network width
  • kernel size
  • image classification
  • CIFAR-10
  • model performance comparison

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Buss, E., Radmann, É., Conceição, R., Zatt, B., & Agostini, L. V. (2025). CNN Architecture Assessment: Exploring Depth, Width, and Kernel Size for Image Classification. Escola Regional de Aprendizado de Máquina e Inteligência Artificial da Região Sul (ERAMIA-RS), 424–427. https://doi.org/10.5753/eramiars.2025.16782

How many times has this paper been cited?

1 times, according to OpenAlex on 18 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at Escola Regional de Aprendizado de Máquina e Inteligência Artificial da Região Sul (ERAMIA-RS): sign in and open the PDF from this page.

Who wrote this paper?

Eduardo Buss, Érick Radmann, Ruhan Conceição, Bruno Zatt, Luciano Volcan Agostini.

What is the DOI of this paper?

10.5753/eramiars.2025.16782, permanently at https://doi.org/10.5753/eramiars.2025.16782. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 18 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.