Can using a pre-trained deep learning model as the feature extractor in the bag-of-deep-visual-words model always improve image classification accuracy?

• Ye Xu ,

  Roles Conceptualization, Formal analysis, Funding acquisition, Methodology, Resources, Software, Validation, Visualization, Writing – original draft, Writing – review & editing

  * E-mail: xuye@wxit.edu.cn

  Affiliation School of IoT Technology, Wuxi Institute of Technology, Wuxi, Jiangsu, China

  https://orcid.org/0000-0002-3361-0177

  ⨯
• Xin Zhang,

  Roles Data curation, Investigation, Validation, Visualization

  Affiliation School of IoT Technology, Wuxi Institute of Technology, Wuxi, Jiangsu, China

  ⨯
• Chongpeng Huang,

  Roles Project administration, Resources, Supervision, Writing – review & editing

  Affiliation School of IoT Technology, Wuxi Institute of Technology, Wuxi, Jiangsu, China

  ⨯
• Xiaorong Qiu

  Roles Conceptualization, Investigation, Methodology, Writing – review & editing

  Affiliation School of IoT Technology, Wuxi Institute of Technology, Wuxi, Jiangsu, China

  ⨯