Image classification based on unsupervised adversarial transfer learning and preserving the inter-class and intra-class distance

Document Type : Original Article

Authors

1 University of Tabriz

2 Faculty of Electrical and Computer Engineering, University of Tabriz

3 İstinye university

Abstract

The paper explores the growing use of deep learning in machine vision, acknowledging challenges in model generalizability due to insufficient data. To address this issue, the proposed solution employs multi-source unsupervised adversarial transfer learning, enhancing adaptability across diverse datasets. This approach compels the network to learn shared features between different datasets rather than domain-specific ones. A novel loss function is introduced, emphasizing inter-class and intra-class distance preservation. This enhances the network's ability to learn similar representations for samples within the same class and dissimilar representations for instances across different classes. Evaluation involves testing on MNIST, MNIST-M, SVHN, and USPS datasets under various transmission scenarios. Comparative analysis with other algorithms demonstrates the effectiveness of the proposed approach, achieving accuracies of 99.5%, 98.8%, 98.5%, and 98.2% for MNIST, MNIST-M, SVHN, and USPS datasets, respectively. The results highlight the solution's success in addressing insufficient data challenges and improving model generalizability in machine vision applications

Keywords

Main Subjects

References

[1] V. Esmaeili, M. Mohassel Feghhi, and S. O. Shahdi, "Applying Partial Differential Equations on Cubic Uniform Local Binary Pattern to Reveal Micro-Changes," Journal of Electrical and Computer Engineering Innovations (JECEI), vol. 12, no. 1, pp. 259-270, 2024, doi: 10.22061/jecei.2023.9600.639.
[2] M. Ghaderzadeh, M. Aria, and F. Asadi, "X-Ray Equipped with Artificial Intelligence: Changing the COVID-19 Diagnostic Paradigm during the Pandemic," BioMed Research International, vol. 2021, p. 9942873, 2021/08/26 2021, doi: 10.1155/2021/9942873.
[3] V. Esmaeili, M. Mohassel Feghhi, and S. O. Shahdi, "Spotting micro-movements in image sequence by introducing intelligent cubic-LBP," IET Image Processing, vol. 16, no. 14, pp. 3814-3830, 2022, doi: https://doi.org/10.1049/ipr2.12596.
[4] V. Esmaeili, M. Mohassel Feghhi, and S. O. Shahdi, "A comprehensive survey on facial micro-expression: approaches and databases," Multimedia Tools and Applications, vol. 81, no. 28, pp. 40089-40134, 2022/11/01 2022, doi: 10.1007/s11042-022-13133-2.
[5] A. N. Hassan, M. Mohassel Feghhi, and V. Esmaeili, "A Fast Automatic Modulation Classification Based on STFT Using Hybrid Deep Neural Network," Journal of Communication Engineering, vol. 10, no. 2, pp. -, 2021, doi: 10.22070/jce.2023.17933.1250.
[6] V. Esmaeili and M. Mohassel Feghhi, "Real-time Authentication for Electronic Service Applicants using a Method Based on Two-Stream 3D Deep Learning," Soft Computing Journal, pp. -, 2023, doi: 10.22052/scj.2023.246701.1086.
[7] A. Farhad et al., "Artificial intelligence in estimating fractional flow reserve: a systematic literature review of techniques," BMC Cardiovascular Disorders, vol. 23, no. 1, p. 407, 2023/08/18 2023, doi: 10.1186/s12872-023-03447-w.
[8] M. Ghaderzadeh, M. Aria, A. Hosseini, F. Asadi, D. Bashash, and H. Abolghasemi, "A fast and efficient CNN model for B-ALL diagnosis and its subtypes classification using peripheral blood smear images," International Journal of Intelligent Systems, vol. 37, no. 8, pp. 5113-5133, 2022, doi: https://doi.org/10.1002/int.22753.
Advanced Signal Processing
Volume 6, Issue 2 - Serial Number 9
September 2025
Pages 253-261

Files

Share

How to cite

Statistics