Performance Improvement of Pre-trained Convolutional Neural Networks for Action Recognition


ÖZCAN T., BAŞTÜRK A.

Computer Journal, cilt.64, sa.11, ss.1715-1730, 2021 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 64 Sayı: 11
  • Basım Tarihi: 2021
  • Doi Numarası: 10.1093/comjnl/bxaa029
  • Dergi Adı: Computer Journal
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, ABI/INFORM, Aerospace Database, Applied Science & Technology Source, Communication Abstracts, Compendex, Computer & Applied Sciences, INSPEC, Metadex, MLA - Modern Language Association Database, zbMATH, Civil Engineering Abstracts
  • Sayfa Sayıları: ss.1715-1730
  • Anahtar Kelimeler: convolutional neural networks, action recognition, artificial bee colony algorithm, transfer learning, pre-trained models, CLASSIFICATION, OPTIMIZATION, ARCHITECTURES, SELECTION
  • Erciyes Üniversitesi Adresli: Evet

Özet

© 2020 The British Computer Society 2020. All rights reserved.Action recognition is a challenging task. Deep learning models have been investigated to solve this problem. Setting up a new neural network model is a crucial and time-consuming process. Alternatively, pre-trained convolutional neural network (CNN) models offer rapid modeling. The selection of the hyperparameters of CNNs is a challenging issue that heavily depends on user experience. The parameters of CNNs should be carefully selected to get effective results. For this purpose, the artificial bee colony (ABC) algorithm is used for tuning the parameters to get optimum results. The proposed method includes three main stages: the image preprocessing stage involves automatic cropping of the meaningful area within the images in the data set, the transfer learning stage includes experiments with six different pre-trained CNN models and the hyperparameter tuning stage using the ABC algorithm. Performance comparison of the pre-trained CNN models involving the use and nonuse of the ABC algorithm for the Stanford 40 data set is presented. The experiments show that the pre-trained CNN models with ABC are more successful than pre-trained CNN models without ABC. Additionally, to the best of our knowledge, the improved NASNet-Large CNN model with the ABC algorithm gives the best accuracy of 87.78% for the overall success rate-based performance metric.