Effects of Brightness and Class-Unbalanced Dataset on CNN Model Selection and Image Classification Considering Autonomous Driving

Zhumakhan Nazir, Vladislav Yarovenko, Jurn Gyu Park

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In addition to an approach of combining machine learning (ML) enhanced models and convolutional neural networks (CNNs) for adaptive CNN model selection, a thorough investigation study of the effects of 1) image brightness and 2) class-balanced/-unbalanced datasets is needed, considering image classification (and object detection) for autonomous driving in significantly different daytime and nighttime settings. In this empirical study, we comprehensively investigate the effects of these two main issues on CNN performance by using the ImageNet dataset, predictive models (premodel), and CNN models. Based on the experimental results and analysis, we reveal non-trivial pitfalls (up to 58% difference in top-1 accuracy in different class-balance datasets) and opportunities in classification accuracy by changing brightness levels and class-balance ratios in datasets.

Original languageEnglish
Title of host publicationNeural Information Processing - 30th International Conference, ICONIP 2023, Proceedings
EditorsBiao Luo, Long Cheng, Zheng-Guang Wu, Hongyi Li, Chaojie Li
PublisherSpringer Science and Business Media Deutschland GmbH
Pages191-203
Number of pages13
ISBN (Print)9789819981830
DOIs
Publication statusPublished - 2024
Event30th International Conference on Neural Information Processing, ICONIP 2023 - Changsha, China
Duration: Nov 20 2023Nov 23 2023

Publication series

NameCommunications in Computer and Information Science
Volume1969 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference30th International Conference on Neural Information Processing, ICONIP 2023
Country/TerritoryChina
CityChangsha
Period11/20/2311/23/23

Keywords

  • Balanced Dataset
  • CNNs
  • Image Feature Extraction
  • Interpretable Models

ASJC Scopus subject areas

  • General Computer Science
  • General Mathematics

Fingerprint

Dive into the research topics of 'Effects of Brightness and Class-Unbalanced Dataset on CNN Model Selection and Image Classification Considering Autonomous Driving'. Together they form a unique fingerprint.

Cite this