Conference paper · 2019 · Open access
Evolution of Convolutional Neural Network Architecture in Image Classification Problems
International Scientific and Practical Conference "Information Technologies and Security" (ITS), 35–45 · Published 20 February 2019 · DOI 10.55056/ceur-ws.org/vol-2318/paper4
In brief
“Evolution of Convolutional Neural Network Architecture in Image Classification Problems” is a 2019 conference paper by Andrey Arsenov and 3 co-authors, published in International Scientific and Practical Conference "Information Technologies and Security" (ITS). OpenAlex counts 18 citations as of 18 November 2026. It is open access: the full text is free to read at International Scientific and Practical Conference "Information Technologies and Security" (ITS).
- Citations
- 18
- Most cited in
- 2019 (6)
- Field-weighted impact
- 1.04
- References
- 9
- Authors
- 4
Abstract
At present, the models and computer vision algorithms are increa- singly used in various fields of activity. For example, in systems of sample analysis in medicine and pharmacology, in identification of individuals by a fingerprint, iris or face, in video surveillance security systems and in many oth- er systems and applications. In connection with the growth of computing power and the emergence of big databases of images, it became possible to learn and use deep neural networks for solving the problems of classification and recogni- tion. As to the image classification problem, the Convolutional Neural Net- works showed themselves best of all; every year since 2012, they won the pres- tigious international contest – the ImageNet Large Scale Visual Classification Challenge (ILSVRC), in which such giants as Google and Microsoft partici- pated. Thanks to the revealing of their capabilities, the convolutional neural networks are increasingly used for pattern recognition, image classification, ob- ject detection, semantic segmentation, and solving many other problems. The paper examines the evolution of the most efficient models and trends in devel- opment of architecture of convolutional neural networks, which are currently used for classification of images that have been included in the list of winners of this international competition, ILSVRC. More precisely, the key features of architecture and its annual variations are revealed on the background of increas- ing efficiency of practical application of these networks. The data of numerous experiments conducted over the past few years are summarized, classes of ap- plied problems are analyzed, and estimates are given for an effectiveness of use of the considered convolutional neural networks. In fact, these performance es- timates are based on evaluation of probability of adequate classification of im- ages. On this basis, a generalized algorithm is formulated, and practical recom- mendations are proposed taking into account the problem features.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Arsenov, A., Рубан, І. В., Smelyakov, K., & Chupryna, A. (2019). Evolution of Convolutional Neural Network Architecture in Image Classification Problems. International Scientific and Practical Conference "Information Technologies and Security" (ITS), 35–45. https://doi.org/10.55056/ceur-ws.org/vol-2318/paper4
MLA 9
Arsenov, Andrey, et al. “Evolution of Convolutional Neural Network Architecture in Image Classification Problems.” International Scientific and Practical Conference "Information Technologies and Security" (ITS), 2019, pp. 35–45. https://doi.org/10.55056/ceur-ws.org/vol-2318/paper4.
Chicago
Arsenov, Andrey, Ігор Вікторович Рубан, Kirill Smelyakov, and Anastasiya Chupryna. 2019. “Evolution of Convolutional Neural Network Architecture in Image Classification Problems.” International Scientific and Practical Conference "Information Technologies and Security" (ITS): 35–45. https://doi.org/10.55056/ceur-ws.org/vol-2318/paper4.
Harvard
Arsenov, A. et al. (2019) ‘Evolution of Convolutional Neural Network Architecture in Image Classification Problems’, International Scientific and Practical Conference "Information Technologies and Security" (ITS), pp. 35–45. doi:10.55056/ceur-ws.org/vol-2318/paper4.
IEEE
A. Arsenov, І. В. Рубан, K. Smelyakov, and A. Chupryna, “Evolution of Convolutional Neural Network Architecture in Image Classification Problems,” International Scientific and Practical Conference "Information Technologies and Security" (ITS), pp. 35–45, 2019, doi: 10.55056/ceur-ws.org/vol-2318/paper4.
BibTeX
@inproceedings{arsenov2019evolution,
title = {{Evolution of Convolutional Neural Network Architecture in Image Classification Problems}},
author = {Arsenov, Andrey and Рубан, Ігор Вікторович and Smelyakov, Kirill and Chupryna, Anastasiya},
booktitle = {International Scientific and Practical Conference "Information Technologies and Security" (ITS)},
year = {2019},
pages = {35--45},
doi = {10.55056/ceur-ws.org/vol-2318/paper4},
url = {https://doi.org/10.55056/ceur-ws.org/vol-2318/paper4}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2019 | 6 | |
| 2020 | 6 | |
| 2021 | 1 | |
| 2022 | 1 | |
| 2023 | 2 | |
| 2024 | 1 | |
| 2026 | 1 |
Its field-weighted citation impact is 1.04: it has been cited 1.04 times as often as the average work of the same field, type and year (1.00 is the world average).
Topic and keywords
Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- convolutional neural networks
- image classification
- classification accuracy
- pattern recognition
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Arsenov, A., Рубан, І. В., Smelyakov, K., & Chupryna, A. (2019). Evolution of Convolutional Neural Network Architecture in Image Classification Problems. International Scientific and Practical Conference "Information Technologies and Security" (ITS), 35–45. https://doi.org/10.55056/ceur-ws.org/vol-2318/paper4
How many times has this paper been cited?
18 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 International Scientific and Practical Conference "Information Technologies and Security" (ITS): sign in and open the PDF from this page.
Who wrote this paper?
Andrey Arsenov, Ігор Вікторович Рубан, Kirill Smelyakov, Anastasiya Chupryna.
What is the DOI of this paper?
10.55056/ceur-ws.org/vol-2318/paper4, permanently at https://doi.org/10.55056/ceur-ws.org/vol-2318/paper4. 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.