Volume 21, Issue 4 (3-2025)
JSDP 2025, 21(4): 49-66 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Gholizade M, soltanizadeh H, Rahmanimanesh M. Multi-Source Transfer Learning Based on Fuzzy Rules for Improving Image Classification Accuracy. JSDP 2025; 21 (4) : 4
URL: http://jsdp.rcisp.ac.ir/article-1-1401-en.html
URL: http://jsdp.rcisp.ac.ir/article-1-1401-en.html
Semnan University & Associate Professors, Faculty of Electrical and Computer Engineering, Semnan University, Semnan, Iran
Abstract: (383 Views)
Image classification tasks often involve the challenge of acquiring a sufficient number of labeled training samples, a process that is not only expensive but also time-consuming. In response to this issue, researchers have focused on transfer learning algorithms, which capitalize on prior knowledge to enhance a model training. While numerous existing transfer learning methods concentrate on knowledge transfer between a single-source domain and a single-target domain, the complexity of real-world scenarios is often underestimated. Limited studies have delved into domain adaptation within multi-source environments, where transferring knowledge from multiple sources introduces ambiguity and uncertainty into the learning process. To address this challenge, this study proposes the application of fuzzy rule-based transfer learning, leveraging the inherent ability of fuzzy rules to effectively handle uncertainty.
One notable aspect of fuzzy transfer learning, and transfer learning in general, is the unresolved question of effectively combining and utilizing knowledge when multiple source domains are available. This issue is particularly pertinent in scenarios involving diverse datasets from various sources. Consequently, the present study introduces a novel approach to multi-source transfer learning anchored in fuzzy rules. By integrating fuzzy logic, the proposed method aims to provide a robust solution to the challenges posed by knowledge transfer in scenarios with multiple source domains. This research contributes to advancing transfer learning methodologies, offering a nuanced perspective on handling uncertainty in multi-source environments by applying fuzzy rule-based techniques.
In conclusion, the significance of transfer learning in image classification tasks is underscored by the inherent challenges of acquiring labeled training data. The conventional focus on single-source to single-target domain transfer has limitations, prompting a shift towards addressing the more realistic and challenging scenarios of multi-source domain adaptation. This study introduces a pioneering approach to multi-source transfer learning, utilizing fuzzy rule-based techniques to effectively navigate the complexities introduced by knowledge transfer from multiple sources. Through this contribution, the research aims to propel advancements in transfer learning methodologies and foster a more comprehensive understanding of handling uncertainty in multi-source environments.
One notable aspect of fuzzy transfer learning, and transfer learning in general, is the unresolved question of effectively combining and utilizing knowledge when multiple source domains are available. This issue is particularly pertinent in scenarios involving diverse datasets from various sources. Consequently, the present study introduces a novel approach to multi-source transfer learning anchored in fuzzy rules. By integrating fuzzy logic, the proposed method aims to provide a robust solution to the challenges posed by knowledge transfer in scenarios with multiple source domains. This research contributes to advancing transfer learning methodologies, offering a nuanced perspective on handling uncertainty in multi-source environments by applying fuzzy rule-based techniques.
In conclusion, the significance of transfer learning in image classification tasks is underscored by the inherent challenges of acquiring labeled training data. The conventional focus on single-source to single-target domain transfer has limitations, prompting a shift towards addressing the more realistic and challenging scenarios of multi-source domain adaptation. This study introduces a pioneering approach to multi-source transfer learning, utilizing fuzzy rule-based techniques to effectively navigate the complexities introduced by knowledge transfer from multiple sources. Through this contribution, the research aims to propel advancements in transfer learning methodologies and foster a more comprehensive understanding of handling uncertainty in multi-source environments.
Article number: 4
Type of Study: Research |
Subject:
Paper
Received: 2023/10/14 | Accepted: 2024/12/4 | Published: 2025/04/2 | ePublished: 2025/04/2
Received: 2023/10/14 | Accepted: 2024/12/4 | Published: 2025/04/2 | ePublished: 2025/04/2
References
1. F. Liu, J. Lu, and G. Zhang, "Unsupervised Heterogeneous Domain Adaptation via Shared Fuzzy Equivalence Relations," IEEE Trans. Fuzzy Syst., vol. 26, no. 6, pp. 3555-3568, Dec. 2018, doi: 10.1109/TFUZZ.2018.2836364. [DOI:10.1109/TFUZZ.2018.2836364]
2. Y. Yin, Z. Yang, H. Hu, and X. Wu, "Universal multi-Source domain adaptation for image classification," Pattern Recognit., vol. 121, 2022, doi: 10.1016/j.patcog.2021.108238. [DOI:10.1016/j.patcog.2021.108238]
3. "Granular fuzzy regression domain adaptation in Takagi-Sugeno fuzzy models".
4. C. Yang, Y. M. Cheung, J. Ding, K. C. Tan, B. Xue, and M. Zhang, "Contrastive Learning Assisted-Alignment for Partial Domain Adaptation," IEEE Trans. Neural Networks Learn. Syst., 2022, doi: 10.1109/TNNLS.2022.3145034. [DOI:10.1109/TNNLS.2022.3145034] [PMID]
5. M. Gholizade, H. Soltanizadeh, and M. Rahmanimanesh, "A Survey of Transfer Learning and Categories," Model. Simul. Electr. Electron. Eng., vol. 1, no. 3, pp. 17-25, 2021, doi: 10.22075/mseee.2021.23310.1062.
6. M. Gholizade, M. Rahmanimanesh, H. Soltanizadeh, and S. S. Sana, "Hesitant triangular fuzzy FlowSort method: the multi-criteria decision-making problems," Int. J. Syst. Sci. Oper. Logist., vol. 10, no. 1, 2023, doi: 10.1080/23302674.2023.2259293. [DOI:10.1080/23302674.2023.2259293]
7. B. Tan, E. Zhong, E. W. Xiang, and Q. Yang, "Multi-transfer: Transfer learning with multiple views and multiple sources," Stat. Anal. Data Min., vol. 7, no. 4, pp. 282-293, 2014, doi: 10.1002/sam.11226. [DOI:10.1002/sam.11226]
8. D. K. Nguyen, W. L. Tseng, and H. H. Shuai, "Domain-Adaptive Object Detection via Uncertainty-Aware Distribution Alignment," MM 2020 - Proc. 28th ACM Int. Conf. Multimed., pp. 2499-2507, 2020, doi: 10.1145/3394171.3413553. [DOI:10.1145/3394171.3413553]
9. V. Chouhan et al., "A Novel Transfer Learning Based Approach for Pneumonia Detection in Chest X-ray Images," Appl. Sci., vol. 10, no. 2, p. 559, Jan. 2020, doi: 10.3390/app10020559. [DOI:10.3390/app10020559]
10. S. F. Nourollahi, R. Baradaran, and H. Amirkhani, "Domain adaptation-based method for improving generalization of hate speech detection models," Signal Data Process., vol. 21, no. 1, pp. 125-142, Jun. 2024, doi: 10.61186/jsdp.21.1.125. [DOI:10.61186/jsdp.21.1.125]
11. Y. Zhu et al., "Deep subdomain adaptation network for image classification," IEEE Trans. Neural Networks Learn. Syst., vol. 32, no. 4, pp. 1713-1722, 2021, doi: 10.1109/TNNLS.2020.2988928. [DOI:10.1109/TNNLS.2020.2988928] [PMID]
12. J. Lu, H. Zuo, and G. Zhang, "Fuzzy Multiple-Source Transfer Learning," IEEE Trans. Fuzzy Syst., vol. 28, no. 12, pp. 3418-3431, 2020, doi: 10.1109/TFUZZ.2019.2952792. [DOI:10.1109/TFUZZ.2019.2952792]
13. H. Zuo, G. Zhang, W. Pedrycz, V. Behbood, and J. Lu, "Fuzzy Regression Transfer Learning in Takagi-Sugeno Fuzzy Models," IEEE Trans. Fuzzy Syst., vol. 25, no. 6, pp. 1795-1807, 2017, doi: 10.1109/TFUZZ.2016.2633376. [DOI:10.1109/TFUZZ.2016.2633376]
14. H. Zuo, G. Zhang, W. Pedrycz, V. Behbood, and J. Lu, "Granular Fuzzy Regression Domain Adaptation in Takagi-Sugeno Fuzzy Models," IEEE Trans. Fuzzy Syst., vol. 26, no. 2, pp. 847-858, 2018, doi: 10.1109/TFUZZ.2017.2694801. [DOI:10.1109/TFUZZ.2017.2694801]
15. H. Zuo, J. Lu, G. Zhang, and W. Pedrycz, "Fuzzy Rule-Based Domain Adaptation in Homogeneous and Heterogeneous Spaces," IEEE Trans. Fuzzy Syst., vol. 27, no. 2, pp. 348-361, 2019, doi: 10.1109/TFUZZ.2018.2853720. [DOI:10.1109/TFUZZ.2018.2853720]
16. E. Khaleghi, H. Solatanzadeh, and M. Gholizadeh, "Recognition of gait disorder in people with knee joint disability using FUZZY system," J. Mach. Vis. Image Process., vol. 9, no. 2, pp. 33-45, 2022, [Online]. Available: http://jmvip.sinaweb.net/article_139030.html
17. S. K. Meher and N. S. Kothari, "Interpretable Rule-Based Fuzzy ELM and Domain Adaptation for Remote Sensing Image Classification," IEEE Trans. Geosci. Remote Sens., vol. 59, no. 7, pp. 5907-5919, 2021, doi: 10.1109/TGRS.2020.3024796. [DOI:10.1109/TGRS.2020.3024796]
18. Z. Deng, Y. Jiang, F. L. Chung, H. Ishibuchi, and S. Wang, "Knowledge-leverage-based fuzzy system and its modeling," IEEE Trans. Fuzzy Syst., vol. 21, no. 4, pp. 597-609, 2013, doi: 10.1109/TFUZZ.2012.2212444. [DOI:10.1109/TFUZZ.2012.2212444]
19. V. Behbood, J. Lu, and G. Zhang, "Fuzzy refinement domain adaptation for long term prediction in banking ecosystem," IEEE Trans. Ind. Informatics, vol. 10, no. 2, pp. 1637-1646, 2014, doi: 10.1109/TII.2012.2232935. [DOI:10.1109/TII.2012.2232935]
20. K. Li, J. Lu, H. Zuo, and G. Zhang, "Multi-Source Contribution Learning for Domain Adaptation," IEEE Trans. Neural Networks Learn. Syst., vol. 33, no. 10, pp. 5293-5307, 2022, doi: 10.1109/TNNLS.2021.3069982. [DOI:10.1109/TNNLS.2021.3069982] [PMID]
21. K. Li, J. Lu, H. Zuo, and G. Zhang, "Source-Free Multi-Domain Adaptation with Fuzzy Rule-based Deep Neural Networks," IEEE Trans. Fuzzy Syst., 2023, doi: 10.1109/TFUZZ.2023.3276978. [DOI:10.1109/TFUZZ.2023.3276978]
22. K. Li, J. Lu, H. Zuo, and G. Zhang, "Multi-Source Contribution Learning for Domain Adaptation," IEEE Trans. Neural Networks Learn. Syst., 2021, doi: 10.1109/TNNLS.2021.3069982. [DOI:10.1109/TNNLS.2021.3069982] [PMID]
23. K. Li, J. Lu, H. Zuo, and G. Zhang, "Dynamic Classifier Alignment for Unsupervised Multi-Source Domain Adaptation," IEEE Trans. Knowl. Data Eng., vol. 35, no. 5, pp. 4727-4740, 2023, doi: 10.1109/TKDE.2022.3144423. [DOI:10.1109/TKDE.2022.3144423]
24. H. Zuo, J. Lu, G. Zhang, and F. Liu, "Fuzzy Transfer Learning Using an Infinite Gaussian Mixture Model and Active Learning," IEEE Trans. Fuzzy Syst., vol. 27, no. 2, pp. 291-303, 2019, doi: 10.1109/TFUZZ.2018.2857725. [DOI:10.1109/TFUZZ.2018.2857725]
25. K. Li, J. Lu, H. Zuo, and G. Zhang, "Multi-Source Domain Adaptation with Fuzzy-Rule based Deep Neural Networks," IEEE Int. Conf. Fuzzy Syst., vol. 2021-July, 2021, doi: 10.1109/FUZZ45933.2021.9494586. [DOI:10.1109/FUZZ45933.2021.9494586]
26. F. Liu, G. Zhang, and J. Lu, "Multisource Heterogeneous Unsupervised Domain Adaptation via Fuzzy Relation Neural Networks," IEEE Trans. Fuzzy Syst., vol. 29, no. 11, pp. 3308-3322, 2021, doi: 10.1109/TFUZZ.2020.3018191. [DOI:10.1109/TFUZZ.2020.3018191]
27. J. Wang, Y. Chen, W. Feng, Y. U. Han, M. Huang, and Q. Yang, "Transfer learning with dynamic distribution adaptation," ACM Trans. Intell. Syst. Technol., vol. 11, no. 1, 2020, doi: 10.1145/3360309. [DOI:10.1145/3360309]
28. Y. Ganin and V. Lempitsky, "Unsupervised domain adaptation by backpropagation," 32nd Int. Conf. Mach. Learn. ICML 2015, vol. 2, pp. 1180-1189, 2015.
29. M. Long, Y. Cao, J. Wang, and M. I. Jordan, "Learning transferable features with deep adaptation networks," 32nd Int. Conf. Mach. Learn. ICML 2015, vol. 1, pp. 97-105, 2015.
30. Y. Zhu et al., "Multi-representation adaptation network for cross-domain image classification," Neural Networks, vol. 119, pp. 214-221, 2019, doi: 10.1016/j.neunet.2019.07.010. [DOI:10.1016/j.neunet.2019.07.010] [PMID]
31. B. Sun and K. Saenko, "Deep CORAL: Correlation alignment for deep domain adaptation," Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 9915 LNCS, pp. 443-450, 2016, doi: 10.1007/978-3-319-49409-8_35. [DOI:10.1007/978-3-319-49409-8_35]
32. R. Xu, Z. Chen, W. Zuo, J. Yan, and L. Lin, "Deep Cocktail Network: Multi-source Unsupervised Domain Adaptation with Category Shift," Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., pp. 3964-3973, 2018, doi: 10.1109/CVPR.2018.00417. [DOI:10.1109/CVPR.2018.00417]
33. Y. Zhu, F. Zhuang, and D. Wang, "Aligning domain-specific distribution and classifier for cross-domain classification from multiple sources," 33rd AAAI Conf. Artif. Intell. AAAI 2019, 31st Innov. Appl. Artif. Intell. Conf. IAAI 2019 9th AAAI Symp. Educ. Adv. Artif. Intell. EAAI 2019, pp. 5989-5996, 2019, doi: 10.1609/aaai.v33i01.33015989. [DOI:10.1609/aaai.v33i01.33015989]
34. K. Li, J. Lu, H. Zuo, and G. Zhang, "Multi-Source Domain Adaptation with Distribution Fusion and Relationship Extraction," Proc. Int. Jt. Conf. Neural Networks, 2020, doi: 10.1109/IJCNN48605.2020.9207556. [DOI:10.1109/IJCNN48605.2020.9207556]
35. K. Li, J. Lu, H. Zuo, and G. Zhang, "Multidomain Adaptation with Sample and Source Distillation," IEEE Trans. Cybern., vol. 54, no. 4, pp. 2193-2205, 2024, doi: 10.1109/TCYB.2023.3236008. [DOI:10.1109/TCYB.2023.3236008] [PMID]
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
