Analysis of Transfer Learning Factors in CNN-Based Image Classification Performance (CNN 기반 영상 분류 성능에 대한 전이학습 요인 분석)

Woo Jung Ahn (안우중); In Seop Na (나인섭)

doi:10.20465/KIOTS.2025.11.6.163

Analysis of Transfer Learning Factors in CNN-Based Image Classification Performance

Journal of Internet of Things and Convergence
Abbr : JKIOTS
2025, 11(6), pp.175~180
DOI : 10.20465/KIOTS.2025.11.6.163
Publisher : The Korea Internet of Things Society
Research Area : Engineering > Computer Science > Internet Information Processing
Received : November 28, 2025
Accepted : December 17, 2025
Published : December 31, 2025

Woo Jung Ahn ¹, In Seop Na ²

¹전남대 데이터사이언스대학원
²전남대학교

Accredited

ABSTRACT

This study experimentally analyzed the effects of domain similarity, backbone complexity, and transfer strategy on image classification performance in CNN-based transfer learning. After pre-training on CIFAR-10 as the source domain, a 2×2×2 factorial design experiment was conducted applying Feature Extraction and Fine-Tuning strategies using VGG16 and InceptionV3 backbones on STL-10 (similar domain) and Fashion-MNIST (dissimilar domain). The experimental results showed that the combination of InceptionV3 and Fine-Tuning achieved the highest performance with 90.5% accuracy in the similar domain, while the combination of VGG16 and Feature Extraction maintained stable performance of 78.6% in the dissimilar domain. This study demonstrated that transfer learning performance is determined by the interaction among three factors rather than a single factor, and provides practical guidelines for selecting strategies in domain adaptation and small-scale data transfer learning design.

KEYWORDS

Transfer Learning, CNN, Domain Similarity, Fine-Tuning, Feature Extraction, Image, Classification

Journal Copyright Policy

No CCL information provided

Citation status

* References for papers published after 2025 are currently being built.

[confproc] Yosinski, J. / 2014 / How transferable are features in deep neural networks? / Advances in Neural Information Processing Systems 27

[confproc] Szegedy C. / 2016 / Rethinking the Inception architecture for computer vision / Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition : 2818~2826

[confproc] Krizhevsky, A. / 2012 / ImageNet classification with deep convolutional neural networks / Advances in Neural Information Processing Systems 25 : 1097~1105

[other] Simonyan, K. / 2014 / Very Deep Convolutional Networks for Large-Scale Image Recognition

[journal] Pan, S. J. / 2010 / A Survey on Transfer Learning / IEEE Transactions on Knowledge and Data Engineering 22(10) : 1345~1359

[confproc] Bengio, Y. / 2012 / Deep learning of representations for unsupervised and transfer learning / ICML Workshop on Unsupervised and Transfer Learning : 17~36

[confproc] Ben-David, S. / 2007 / Analysis of representations for domain adaptation / Advances in Neural Information Processing Systems

[confproc] Kornblith, S. / 2019 / Do better ImageNet models transfer better? / Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition : 2661~2671

[confproc] Donahue, J. / 2014 / DeCAF: A deep convolutional activation feature for generic visual recognition / International Conference on Machine Learning : 647~655

[confproc] Ioffe, S. / 2015 / Batch normalization: Accelerating deep network training by reducing internal covariate shift / Proceedings of the 32nd International Conference on Machine Learning

[confproc] He, K. / 2016 / Deep Residual Learning for Image Recognition / Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition : 770~778

[journal] Pan, S. J. / 2010 / A Survey on Transfer Learning / IEEE Transactions on Knowledge and Data Engineering 22(10) : 1345~1359

[confproc] Oquab M. / 2014 / Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks / Proceedings of IEEE Conference on Computer Vision and Pattern Recognition : 1717~1724

[confproc] Yosinski J. / 2014 / How transferable are features in deep neural networks? / Advances in Neural Information Processing Systems 27

[confproc] Kornblith, S. / 2019 / Do better ImageNet models transfer better? / Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition : 2661~2671

[confproc] Tan M. / 2019 / EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks / Proceedings of the 36th International Conference on Machine Learning : 6105~6114

[confproc] Kolesnikov, A. / 2020 / Big transfer (BiT): General visual representation learning / Computer Vision-ECCV 2020 / Springer : 491~507

[confproc] Raghu M. / 2021 / Do Vision Transformers See Like Convolutional Neural Networks? / Advances in Neural Information Processing Systems (NeurIPS) 34 : 12116~12128

KJCKorea
Journal Central

Journal of Internet of Things and Convergence 2025 KCI Impact Factor : 0.75

Analysis of Transfer Learning Factors in CNN-Based Image Classification Performance

ABSTRACT

KEYWORDS

Journal Copyright Policy

Citation status

* References for papers published after 2025 are currently being built.

Journal of Internet of Things and Convergence 2025 KCI Impact Factor : 0.75

Analysis of Transfer Learning Factors in CNN-Based Image Classification Performance

ABSTRACT

KEYWORDS

Journal Copyright Policy

Statistics

Tools

Issue List

Citation status

KCI Citation Counts (0)

REFERENCES (18) * References for papers published after 2025 are currently being built.

Search PDF

Citation

* References for papers published after 2025 are currently being built.