Performance Analysis of GoogleNet on Balanced and Imbalanced Image Classification Datasets
KIET Journal of Computing and Information Sciences · 01.02.2026 · 8 (2)
DOI: 10.51153/kjcis.v82.254 ↗Kurz gefasst
Fachartikel in der Zeitschrift KIET Journal of Computing and Information Sciences, online erschienen am 01.02.2026. Verfasst von Mujeeb Ur Rehman. Die Arbeit nennt 15 Literaturangaben.
Abstract (Originalsprache)
This study has revolutionized image classification by utilizing convolutional neural networks (CNNs). GoogleNet (Inception-v1) serves as a fundamental CNN framework because it incorporated the inception module to boost computational efficiency while maintaining high accuracy. This research explores the performance of GoogleNet on both balanced and unbalanced datasets using CIFAR-10 and CIFAR-100 as test cases. The research examines how well the model adapts while maintaining operational efficiency and classification performance under different testing scenarios. The study first evaluates how model performance is affected by class imbalance and then presents techniques to address this issue while comparing the results to other architecture model.The research investigates contemporary advancements in deep learning by analyzing hybrid models and attention mechanisms which integrate transfer learning techniques. The document evaluates the practical classification performance of GoogleNet while examining its strengths and weaknesses.
Zitieren
APA
Rehman, M. U. (2026). Performance Analysis of GoogleNet on Balanced and Imbalanced Image Classification Datasets. KIET Journal of Computing and Information Sciences, 8(2). https://doi.org/10.51153/kjcis.v82.254
Vancouver
Rehman MU. Performance Analysis of GoogleNet on Balanced and Imbalanced Image Classification Datasets. KIET Journal of Computing and Information Sciences. 2026;8(2). doi:10.51153/kjcis.v82.254
BibTeX
@article{Rehman2026,
author = {Rehman, Mujeeb Ur},
title = {Performance Analysis of GoogleNet on Balanced and Imbalanced Image Classification Datasets},
journal = {KIET Journal of Computing and Information Sciences},
year = {2026},
volume = {8},
number = {2},
doi = {10.51153/kjcis.v82.254}
}
EUVIMED