Computer Optics
RUS  ENG    JOURNALS   PEOPLE   ORGANISATIONS   CONFERENCES   SEMINARS   VIDEO LIBRARY   PACKAGE AMSBIB  
General information
Latest issue
Archive

Search papers
Search references

RSS
Latest issue
Current issues
Archive issues
What is RSS



Computer Optics:
Year:
Volume:
Issue:
Page:
Find






Personal entry:
Login:
Password:
Save password
Enter
Forgotten password?
Register


Computer Optics, 2022, Volume 46, Issue 6, Pages 971–979
DOI: https://doi.org/10.18287/2412-6179-CO-1078
(Mi co1093)
 

NUMERICAL METHODS AND DATA ANALYSIS

Fine-tuning the hyperparameters of pre-trained models for solving multiclass classification problems

D. Kaibassova, M. Nurtay, A. Tau, M. Kissina

Abylkas Saginov Karaganda technical university, 100000, Kazakhstan, Karaganda city, 56 N. Nazarbayev avenue
Abstract: This study is devoted to the application of fine-tuning methods for Transfer Learning models to solve the multiclass image classification problem using the medical X-ray images. To achieve this goal, the structural features of such pre-trained models as VGG-19, ResNet-50, InceptionV3 were studied. For these models, the following fine-tuning methods were used: unfreezing the last convolutional layer and updating its weights, selecting the learning rate and optimizer. As a dataset chest X-Ray images of the Society for Imaging Informatics in Medicine (SIIM), as the leading healthcare organization in its field, in partnership with the Foundation for the Promotion of Health and Biomedical Research of Valencia Region (FISABIO), the Valencian Region Medical ImageBank (BIMCV) ) and the Radiological Society of North America (RSNA) were used. Thus, the results of the experiments carried out illustrated that the pre-trained models with their subsequent tuning are excellent for solving the problem of multiclass classification in the field of medical image processing. It should be noted that ResNet-50 based model showed the best result with 82.74% accuracy. Results obtained for all models are reflected in the corresponding tables.
Keywords: multiclass classification, transfer learning, fine-tuning, CNN, image augmentation, X-ray
Received: 10.12.2021
Accepted: 01.09.2022
Document Type: Article
Language: English
Citation: D. Kaibassova, M. Nurtay, A. Tau, M. Kissina, “Fine-tuning the hyperparameters of pre-trained models for solving multiclass classification problems”, Computer Optics, 46:6 (2022), 971–979
Citation in format AMSBIB
\Bibitem{KaiNurTau22}
\by D.~Kaibassova, M.~Nurtay, A.~Tau, M.~Kissina
\paper Fine-tuning the hyperparameters of pre-trained models for solving multiclass classification problems
\jour Computer Optics
\yr 2022
\vol 46
\issue 6
\pages 971--979
\mathnet{http://mi.mathnet.ru/co1093}
\crossref{https://doi.org/10.18287/2412-6179-CO-1078}
Linking options:
  • https://www.mathnet.ru/eng/co1093
  • https://www.mathnet.ru/eng/co/v46/i6/p971
  • Citing articles in Google Scholar: Russian citations, English citations
    Related articles in Google Scholar: Russian articles, English articles
    Computer Optics
    Statistics & downloads:
    Abstract page:32
    Full-text PDF :20
     
      Contact us:
     Terms of Use  Registration to the website  Logotypes © Steklov Mathematical Institute RAS, 2025