Preprint · 2026 · Open access

Reliable Deep Learning for Small-Scale Classifications: Experiments on Real-World Image Datasets from Bangladesh

Alfe Suny, MD Sakib Ul Islam, Md. Imran Hossain

arXiv (Cornell University) · Published 17 January 2026 · DOI 10.48550/arxiv.2601.11911

Open PDFView at the publisherCite this paper

In brief

“Reliable Deep Learning for Small-Scale Classifications: Experiments on Real-World Image Datasets from Bangladesh” is a 2026 preprint by Alfe Suny and 2 co-authors, published in arXiv (Cornell University). OpenAlex counts 1 citations as of 18 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).

Citations
1
Most cited in
2026 (1)
References
20
Authors
3

Abstract

Convolutional neural networks (CNNs) have achieved state-of-the-art performance in image recognition tasks but often involve complex architectures that may overfit on small datasets. In this study, we evaluate a compact CNN across five publicly available, real-world image datasets from Bangladesh, including urban encroachment, vehicle detection, road damage, and agricultural crops. The network demonstrates high classification accuracy, efficient convergence, and low computational overhead. Quantitative metrics and saliency analyses indicate that the model effectively captures discriminative features and generalizes robustly across diverse scenarios, highlighting the suitability of streamlined CNN architectures for small-class image classification tasks.

Cite this paper

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

APA 7

Suny, A., Islam, M. S. U., & Hossain, M. I. (2026). Reliable Deep Learning for Small-Scale Classifications: Experiments on Real-World Image Datasets from Bangladesh. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2601.11911

MLA 9

Suny, Alfe, et al. “Reliable Deep Learning for Small-Scale Classifications: Experiments on Real-World Image Datasets from Bangladesh.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2601.11911.

Chicago

Suny, Alfe, MD Sakib Ul Islam, and Md. Imran Hossain. 2026. “Reliable Deep Learning for Small-Scale Classifications: Experiments on Real-World Image Datasets from Bangladesh.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2601.11911.

Harvard

Suny, A., Islam, M. S. U. and Hossain, M. I. (2026) ‘Reliable Deep Learning for Small-Scale Classifications: Experiments on Real-World Image Datasets from Bangladesh’, arXiv (Cornell University). doi:10.48550/arxiv.2601.11911.

IEEE

A. Suny, M. S. U. Islam, and M. I. Hossain, “Reliable Deep Learning for Small-Scale Classifications: Experiments on Real-World Image Datasets from Bangladesh,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2601.11911.

BibTeX

@misc{suny2026reliable,
  title     = {{Reliable Deep Learning for Small-Scale Classifications: Experiments on Real-World Image Datasets from Bangladesh}},
  author    = {Suny, Alfe and Islam, MD Sakib Ul and Hossain, Md. Imran},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2601.11911},
  url       = {https://doi.org/10.48550/arxiv.2601.11911}
}

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

  • compact convolutional neural networks
  • overfitting
  • vehicle detection
  • road damage detection
  • crop classification
  • saliency analysis

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?

Suny, A., Islam, M. S. U., & Hossain, M. I. (2026). Reliable Deep Learning for Small-Scale Classifications: Experiments on Real-World Image Datasets from Bangladesh. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2601.11911

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 arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Alfe Suny, MD Sakib Ul Islam, Md. Imran Hossain.

What is the DOI of this paper?

10.48550/arxiv.2601.11911, permanently at https://doi.org/10.48550/arxiv.2601.11911. 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.