Fusion of Explainable Deep Learning Features Using Fuzzy Integral in Computer Vision

dc.authorscopusidWitold Pedrycz / 58861905800
dc.authorwosidWitold Pedrycz / HJZ-2779-2023
dc.contributor.authorWang, Yifan
dc.contributor.authorPedrycz, Witold
dc.contributor.authorIshibuchi, Hisao
dc.contributor.authorZhu, Jihua
dc.date.accessioned2025-04-18T10:06:42Z
dc.date.available2025-04-18T10:06:42Z
dc.date.issued2025
dc.departmentİstinye Üniversitesi, Mühendislik ve Doğa Bilimleri Fakültesi, Bilgisayar Mühendisliği Bölümü
dc.description.abstractFuzzy integral fusion has been shown as an effective tool for enhancing classification accuracy while also achieving explainability. With the deep learning boom in the past decade, many researchers have investigated the advantages of fusing various deep neural networks (DNNs) with fuzzy integral techniques in computer vision. However, recent studies focus on only the explainable fusion process. Thus, features learned by each DNN are difficult to understand. Moreover, DNNs are usually trained on the ImageNet dataset, whereas the effectiveness of applying the fuzzy integral methods to this dataset is yet to be investigated. This is the gap that motivates our research study. To address this issue, we explore fuzzy integral fusion classification models that make both the fusion process and extracted features explainable. Specifically, we use two well-known fuzzy integral fusion methods [i.e., Sugeno integral (SI) and Choquet integral (ChI)] to combine three explainable deep learning features (i.e., shape, texture, and color) in a manner that mimics the human visual recognition process. The originality of our work includes the emphasis on complete explainability in the classification process, the investigation of applying fuzzy integral methods to the ImageNet dataset, and extensive experimental validation of the effectiveness of fuzzy integral. Computational experiments show that fuzzy integral fusion can improve classification accuracy by 14.6% compared with an individual DNN on subsets derived from the ImageNet dataset. Furthermore, fuzzy integral fusion helps understand contributions, relationships, and interactions among the three features (shape, texture, and color) for each class, providing convincing evidence for the final classification result. Consequently, the proposed models not only achieve impressive performance, but also provide a thorough understanding of how these models work. © 1993-2012 IEEE.
dc.identifier.citationWang, Y., Pedrycz, W., Ishibuchi, H., & Zhu, J. (2024). Fusion of Explainable Deep Learning Features Using Fuzzy Integral in Computer Vision. IEEE Transactions on Fuzzy Systems.
dc.identifier.doi10.1109/TFUZZ.2024.3434589
dc.identifier.endpage167
dc.identifier.issn10636706
dc.identifier.issue1
dc.identifier.scopus2-s2.0-85200209028
dc.identifier.scopusqualityQ1
dc.identifier.startpage156
dc.identifier.urihttp://dx.doi.org/10.1109/TFUZZ.2024.3434589
dc.identifier.urihttps://hdl.handle.net/20.500.12713/6946
dc.identifier.volume33
dc.identifier.wosWOS:001394760500034
dc.identifier.wosqualityQ1
dc.indekslendigikaynakScopus
dc.indekslendigikaynakWeb of Science
dc.institutionauthorPedrycz, Witold
dc.institutionauthoridWitold Pedrycz / 0000-0002-9335-9930
dc.language.isoen
dc.publisherInstitute of Electrical and Electronics Engineers Inc.
dc.relation.ispartofIEEE Transactions on Fuzzy Systems
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.subjectChoquet İntegral (ChI)
dc.subjectDeep Learning
dc.subjectExplainable Artificial İntelligence (AI)
dc.subjectExplainable Features
dc.subjectFuzzy İntegral
dc.titleFusion of Explainable Deep Learning Features Using Fuzzy Integral in Computer Vision
dc.typeArticle

Dosyalar

Lisans paketi
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
license.txt
Boyut:
1.17 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama: