Venue & metadata

• Journal/Proceedings: Lecture Notes in Computer Science
• Volume: 15886 LNCS
• Pages: 260 – 273
• Note: Cited by: 0
• Author keywords: Image Classification; Kolmogorov-Arnold Networks; Quantum Convolutional Neural Networks

Abstract

The rapid evolution of Artificial Intelligence has led to significant advancements in image classification, with novel approaches emerging beyond traditional deep learning paradigms. This paper presents a comparative analysis of three distinct methodologies for image classification: classical Convolutional Neural Networks (CNNs), Kolmogorov-Arnold Networks (KANs) and KAN-based CNNs and Quantum Machine Learning using Quantum Convolutional Neural Networks. The study evaluates these models on the Labeled Faces in the Wild dataset, implementing the different classifiers with existing, well-assessed technologies. Given the fundamental differences in computational paradigms, performance assessment extends beyond traditional accuracy metrics to include computational efficiency, interpretability, and, for quantum models, gate depth and noise. As a summary of the results, the proposed Quantum Convolutional Neural Network (QCNN) model achieves an accuracy of 75% on the target images classification task, indicating promising performance within current quantum computational limits. All the experiments strongly suggest that Convolutional Kolmogorov-Arnold Networks (CKANs) exhibit increased accuracy as image resolution decreases, QCNN performance meaningfully changes in relation to noise level, while CNNs still keeping strong discriminative capabilities. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

Keywords

Computational complexity GS Computational efficiency GS Convolution GS Convolutional neural networks GS Deep learning GS Image resolution GS Labeled data GS Learning systems GS Quantum computers GS Quantum theory GS Comparative analyzes GS Convolutional neural network GS Emerging technologies GS Images classification GS Kolmogorov GS Kolmogorov-arnold network GS Learning paradigms GS Network-based GS Performance GS Quantum convolutional neural network GS Image classification GS

Links & artifacts

DOI Publisher Copy BibTeX Download .bib

{"key"=>"Napoli2026260", "type"=>"Conference paper", "bibtex"=>"@article{Napoli2026260,\n  author = {Napoli, Fabio and Castaldo, Mariarosaria and Marrone, Stefano and Campanile, Lelio},\n  title = {Comparing Emerging Technologies in Image Classification: From Quantum to Kolmogorov},\n  year = {2026},\n  journal = {Lecture Notes in Computer Science},\n  volume = {15886 LNCS},\n  pages = {260 – 273},\n  doi = {10.1007/978-3-031-97576-9_17},\n  type = {Conference paper}\n}\n", "author"=>"Napoli, Fabio and Castaldo, Mariarosaria and Marrone, Stefano and Campanile, Lelio", "author_array"=>[{"first"=>"Fabio", "last"=>"Napoli", "prefix"=>"", "suffix"=>""}, {"first"=>"Mariarosaria", "last"=>"Castaldo", "prefix"=>"", "suffix"=>""}, {"first"=>"Stefano", "last"=>"Marrone", "prefix"=>"", "suffix"=>""}, {"first"=>"Lelio", "last"=>"Campanile", "prefix"=>"", "suffix"=>""}], "author_0_first"=>"Fabio", "author_0_last"=>"Napoli", "author_0_prefix"=>"", "author_0_suffix"=>"", "author_1_first"=>"Mariarosaria", "author_1_last"=>"Castaldo", "author_1_prefix"=>"", "author_1_suffix"=>"", "author_2_first"=>"Stefano", "author_2_last"=>"Marrone", "author_2_prefix"=>"", "author_2_suffix"=>"", "author_3_first"=>"Lelio", "author_3_last"=>"Campanile", "author_3_prefix"=>"", "author_3_suffix"=>"", "title"=>"Comparing Emerging Technologies in Image Classification: From Quantum to Kolmogorov", "year"=>"2026", "journal"=>"Lecture Notes in Computer Science", "volume"=>"15886 LNCS", "pages"=>"260 – 273", "doi"=>"10.1007/978-3-031-97576-9_17", "url"=>"https://www.scopus.com/inward/record.uri?eid=2-s2.0-105010835616&doi=10.1007%2f978-3-031-97576-9_17&partnerID=40&md5=07f374de6b9249424b2fb370afa0f113", "abstract"=>"The rapid evolution of Artificial Intelligence has led to significant advancements in image classification, with novel approaches emerging beyond traditional deep learning paradigms. This paper presents a comparative analysis of three distinct methodologies for image classification: classical Convolutional Neural Networks (CNNs), Kolmogorov-Arnold Networks (KANs) and KAN-based CNNs and Quantum Machine Learning using Quantum Convolutional Neural Networks. The study evaluates these models on the Labeled Faces in the Wild dataset, implementing the different classifiers with existing, well-assessed technologies. Given the fundamental differences in computational paradigms, performance assessment extends beyond traditional accuracy metrics to include computational efficiency, interpretability, and, for quantum models, gate depth and noise. As a summary of the results, the proposed Quantum Convolutional Neural Network (QCNN) model achieves an accuracy of 75% on the target images classification task, indicating promising performance within current quantum computational limits. All the experiments strongly suggest that Convolutional Kolmogorov-Arnold Networks (CKANs) exhibit increased accuracy as image resolution decreases, QCNN performance meaningfully changes in relation to noise level, while CNNs still keeping strong discriminative capabilities.  © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.", "author_keywords"=>"Image Classification; Kolmogorov-Arnold Networks; Quantum Convolutional Neural Networks", "keywords"=>"Computational complexity; Computational efficiency; Convolution; Convolutional neural networks; Deep learning; Image resolution; Labeled data; Learning systems; Quantum computers; Quantum theory; Comparative analyzes; Convolutional neural network; Emerging technologies; Images classification; Kolmogorov; Kolmogorov-arnold network; Learning paradigms; Network-based; Performance; Quantum convolutional neural network; Image classification", "publication_stage"=>"Final", "source"=>"Scopus", "note"=>"Cited by: 0"}
    

Suggested citation

Napoli, F., Castaldo, M., Marrone, S., & Campanile, L. (2026). Comparing Emerging Technologies in Image Classification: From Quantum to Kolmogorov [Conference paper]. Lecture Notes in Computer Science, 15886 LNCS, 260–273. https://doi.org/10.1007/978-3-031-97576-9_17