Multilabel Genre Prediction Using Deep-Learning Frameworks

Ünal F. Z., Güzel M. S., Bostancı G. E., Açıcı K., Aşuroğlu T.

APPLIED SCIENCES, cilt.13, sa.15, ss.1-21, 2023 (SCI-Expanded)

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 13 Sayı: 15
  • Basım Tarihi: 2023
  • Doi Numarası: 10.3390/app13158665
  • Dergi Adı: APPLIED SCIENCES
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Aerospace Database, Agricultural & Environmental Science Database, Applied Science & Technology Source, Communication Abstracts, INSPEC, Metadex, Directory of Open Access Journals, Civil Engineering Abstracts
  • Sayfa Sayıları: ss.1-21
  • Ankara Üniversitesi Adresli: Evet

Özet

In this study, transfer learning has been used to overcome multilabel classification tasks. As a case study, movie genre classification by using posters has been chosen. Six state-of-the-art pretrained models, VGG16, ResNet, DenseNet, Inception, MobileNet, and ConvNeXt, have been employed for this experiment. The movie posters have been obtained from Internet Movie Database (IMDB). The dataset has been divided using an iterative stratification technique. A sequence of dense layers has been added on top of each model and these models have been trained and fine-tuned. All the results of the models compared considered accuracy, loss, Hamming loss, F1-score, precision, and AUC metrics. When the metrics used were evaluated, the most successful result regarding accuracy has been obtained from the modified DenseNet architecture at 90%. Also, the ConvNeXt, which is the newest model among all, performed quite satisfactorily, reaching over 90% accuracy. This study uses an iterative stratification method to split an unbalanced dataset which provides more reliable results than the classical splitting method which is the common method in the literature. Also, the feature extraction capabilities of the six pretrained models have been compared. The outcome of this study shows promising results regarding multilabel classification. As for future work, it is planned to enhance this study by using natural language processing and ensemble methods.