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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Suny, Alfe, Islam, MD Sakib Ul, Hossain, Md. Imran
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908797474177024
author Suny, Alfe
Islam, MD Sakib Ul
Hossain, Md. Imran
author_facet Suny, Alfe
Islam, MD Sakib Ul
Hossain, Md. Imran
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_11911
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Reliable Deep Learning for Small-Scale Classifications: Experiments on Real-World Image Datasets from Bangladesh
Suny, Alfe
Islam, MD Sakib Ul
Hossain, Md. Imran
Computer Vision and Pattern Recognition
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.
title Reliable Deep Learning for Small-Scale Classifications: Experiments on Real-World Image Datasets from Bangladesh
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.11911