Balinese Statue Image Classification Using Transfer Learning: A Comparative Study of MobileNetV3 and EfficientNetV2

Dwi Wulandari; Ida Bagus Ary Indra Iswara; I Gede Made  Yudi Antara; I Made Dwi  Putra Asana; I Kadek Dwi  Gandika Supartha

doi:10.52436/1.jutif.2026.7.2.5556

Authors

Dwi Wulandari Informatics, Institut Bisnis dan Teknologi Indonesia, Bali, Indonesia
Ida Bagus Ary Indra Iswara Informatics, Institut Bisnis dan Teknologi Indonesia, Bali, Indonesia
I Gede Made Yudi Antara Informatics, Institut Bisnis dan Teknologi Indonesia, Bali, Indonesia
I Made Dwi Putra Asana Informatics, Institut Bisnis dan Teknologi Indonesia, Bali, Indonesia
I Kadek Dwi Gandika Supartha Informatics, Institut Bisnis dan Teknologi Indonesia, Bali, Indonesia

DOI:

https://doi.org/10.52436/1.jutif.2026.7.2.5556

Keywords:

Balinese Sculpture Classification, Convolutional Neural Networks, Cultural Heritage Preservation, EfficientNetV2, MobileNetV3, Transfer Learning

Abstract

Balinese sculpture is an important form of cultural heritage that exhibits high visual diversity in terms of shape, structure, and carving style, which makes manual identification and documentation challenging. Previous studies on automated statue classification have generally focused on limited sculpture categories and therefore do not fully represent the visual diversity of Balinese sculptures. This study aims to develop an automatic image classification model capable of recognizing multiple Balinese statue categories using transfer learning and fine-tuning strategies. The proposed approach compares two convolutional neural network architectures, MobileNetV3 and EfficientNetV2, across eight statue classes: Dewa, Dewi, Mitologi, Penabuh, Pengapit, Punakawan, Raksasa, and Wanara. A dataset of 8,400 images was constructed from three-dimensional video documentation to capture multiple viewing angles of each statue. The images were processed through frame extraction, resizing, normalization, data augmentation, and dataset splitting. Model training was conducted in two stages, consisting of transfer learning followed by fine-tuning using reduced learning rates. Experimental results indicate that both models achieve high classification performance on the test dataset. MobileNetV3 obtained the highest test accuracy of 99.64% with a loss value of 0.0119, while EfficientNetV2 achieved an accuracy of 98.56% with a loss of 0.0613. These findings demonstrate that lightweight architectures can deliver competitive performance when supported by appropriate training strategies. This study provides a comparative evaluation of efficient deep learning models for cultural heritage image classification and supports the development of more reliable and systematic digital documentation of Balinese sculptures.

Downloads

Download data is not yet available.

References

I. W. Arissusila, I. G. A. Nilawati, and I. P. I. G. P. Sumardiana, “Dinamika Kerajinan Patung Kayu Dalam Mendukung Pariwisata Budaya Bali,” Dharmasmrti: Jurnal Ilmu Agama dan Kebudayaan, vol. 20, no. 2, pp. 154–165, Oct. 2020, doi: 10.32795/ds.v20i2.1039.

M. O. Luruk, A. Y. Rahman, and F. Marisa, “Klasifikasi Jenis Patung Menggunakan Metode Convolutional Neural Network (CNN),” JATISI (Jurnal Teknik Informatika dan Sistem Informasi), vol. 12, no. 1, pp. 201–208, Mar. 2025, doi: 10.35957/jatisi.v12i1.9247.

P. T. Janu Budi Utama, I. K. Sudita, and A. Sudarmawan, “Patung Padas Dan Ragam Hias Yang Ada Di Pura Gunung Sekar Desa Adat Sangsit Dangin Yeh,Kecamatan Sawan, Buleleng, Bali,” Jurnal Pendidikan Seni Rupa Undiksha, vol. 13, no. 2, pp. 151–167, Oct. 2023, doi: 10.23887/jjpsp.v13i2.65676.

A. Herdiansah, R. I. Borman, D. Nurnaningsih, A. A. J. Sinlae, and R. R. Al Hakim, “Klasifikasi Citra Daun Herbal Dengan Menggunakan Backpropagation Neural Networks Berdasarkan Ekstraksi Ciri Bentuk,” JURIKOM (Jurnal Riset Komputer), vol. 9, no. 2, p. 388, Apr. 2022, doi: 10.30865/jurikom.v9i2.4066.

N. L. G. P. Suwirmayanti, I. M. B. Sentana, I. K. G. D. Putra, M. Sudarma, I. M. Sukarsa, and K. Budiarta, “Deep Learning Implementation Using CNN to Classify Bali God Sculpture Pictures,” Lontar Komputer : Jurnal Ilmiah Teknologi Informasi, vol. 15, no. 02, pp. 87–98, Oct. 2025, doi: 10.24843/LKJITI.2024.v15.i02.p02.

F. Ju, “Mapping the Knowledge Structure of Image Recognition in Cultural Heritage: A Scientometric Analysis Using CiteSpace, VOSviewer, and Bibliometrix,” J Imaging, vol. 10, no. 11, p. 272, Oct. 2024, doi: 10.3390/jimaging10110272.

S. Gokak, P. Khichade, N. Heggalagi, A. Billowria, and S. Hegde, “Defect Detection and Classification of Cultural Heritage Buildings Using Deep Learning,” in Proceedings of the 3rd International Conference on Futuristic Technology, SCITEPRESS - Science and Technology Publications, 2025, pp. 619–626. doi: 10.5220/0013633700004664.

Z. Liu, W. Hong, R. Long, Y. Zhu, and X. Zhang, “A lightweight enhanced EfficientNet model for Chinese eaves tile dynasty classification,” npj Heritage Science, vol. 13, no. 1, p. 494, Oct. 2025, doi: 10.1038/s40494-025-02049-3.

A. L. Carvalho Ottoni and L. T. Cordeiro Ottoni, “A deep learning approach for cultural heritage building classification using transfer learning and data augmentation,” J Cult Herit, vol. 74, pp. 214–224, Jul. 2025, doi: 10.1016/j.culher.2025.06.010.

J. Yang, T. Liu, Y. T. Luo, and P. C.-I. Pang, “Deep learning in cultural imagery dissemination: a systematic scoping review of AI-driven visual transmission mechanisms,” Front Commun (Lausanne), vol. 10, Sep. 2025, doi: 10.3389/fcomm.2025.1645168.

F. M. Qotrunnada and P. H. Utomo, “Metode Convolutional Neural Network untuk Klasifikasi Wajah Bermasker,” Prosiding Seminar Nasional Matematika, vol. 5, no. 5, pp. 799–807, 2022.

L. Hakim, H. R. Rahmanto, S. P. Kristanto, and D. Yusuf, “Klasifikasi Citra Motif Batik Banyuwangi Menggunakan Convolutional Neural Network,” Jurnal Teknoinfo, vol. 17, no. 1, p. 203, Jan. 2023, doi: 10.33365/jti.v17i1.2342.

M. Tan and Q. V. Le, “EfficientNetV2: Smaller Models and Faster Training,” in International Conference on Machine Learning, pp. 10096–10106, Jun. 2021, doi: 10.48550/arXiv.2104.00298.

A. Howard et al., “Searching for MobileNetV3,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 1314–24, Nov. 2019, doi: 10.48550/arXiv.1905.02244.

G. Singh, K. Guleria, and S. Sharma, “A Pre-trained EfficientNetV2 Deep Learning Model for Birds Species Classification,” in 2024 3rd International Conference for Advancement in Technology, ICONAT 2024, Institute of Electrical and Electronics Engineers Inc., 2024. doi: 10.1109/ICONAT61936.2024.10774953.

K. DeVoe, G. Takahashi, E. Tarshizi, and A. Sacker, “Evaluation of the precision and accuracy in the classification of breast histopathology images using the MobileNetV3 model,” J Pathol Inform, vol. 15, Dec. 2024, doi: 10.1016/j.jpi.2024.100377.

A. E. Putra, M. F. Naufal, and V. R. Prasetyo, “Klasifikasi Jenis Rempah Menggunakan Convolutional Neural Network dan Transfer Learning,” Jurnal Edukasi dan Penelitian Informatika (JEPIN), vol. 9, no. 1, p. 12, Apr. 2023, doi: 10.26418/jp.v9i1.58186.

P. Yan et al., “A Comprehensive Survey of Deep Transfer Learning for Anomaly Detection in Industrial Time Series: Methods, Applications, and Directions,” IEEE Access, vol. 12, pp. 3768–3789, 2024, doi: 10.1109/ACCESS.2023.3349132.

P. D. Alfano, V. P. Pastore, L. Rosasco, and F. Odone, “Top-tuning: A study on transfer learning for an efficient alternative to fine tuning for image classification with fast kernel methods,” Image Vis Comput, vol. 142, p. 104894, Feb. 2024, doi: 10.1016/j.imavis.2023.104894.

Z. Han, C. Gao, J. Liu, J. Zhang, and S. Q. Zhang, “Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey,” arXiv preprint arXiv:2403.14608, Sep. 2024, doi: 10.48550/arXiv.2403.14608.

N. L. W. S. R. Ginantra, T. Hendrawati, and D. A. P. Wulandari, “Penerapan Metode Stable Diffusion Dengan Fine Tuning Untuk Pola Endek Bali,” TEMATIK, vol. 11, no. 2, pp. 141–147, Nov. 2024, doi: 10.38204/tematik.v11i2.2069.

A. Rahujo, D. Atif, S. A. Inam, A. A. Khan, and S. Ullah, “A survey on the applications of transfer learning to enhance the performance of large language models in healthcare systems,” Discover Artificial Intelligence, vol. 5, no. 1, p. 90, Jun. 2025, doi: 10.1007/s44163-025-00339-0.

T. B. Sasongko, H. Haryoko, and A. Amrullah, “Analisis Efek Augmentasi Dataset dan Fine Tune pada Algoritma Pre-Trained Convolutional Neural Network (CNN),” Jurnal Teknologi Informasi dan Ilmu Komputer, vol. 10, no. 4, pp. 763–768, Aug. 2023, doi: 10.25126/jtiik.2024106583.

Y. Li, M. Ge, M. Li, T. Li, and S. Xiang, “CLIP-Based Adaptive Graph Attention Network for Large-Scale Unsupervised Multi-Modal Hashing Retrieval,” Sensors, vol. 23, no. 7, p. 3439, Mar. 2023, doi: 10.3390/s23073439.

G. Patrucco and F. Setragno, “Enhancing Automation Of Heritage Processes: Generation Of Artificial Training Datasets From Photogrammetric 3d Models,” The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. XLVIII-M-2–2023, pp. 1181–1187, Jun. 2023, doi: 10.5194/isprs-archives-XLVIII-M-2-2023-1181-2023.

E. Nerantzis, L. Malletzidou, E. Kyratzopoulou, N. C. Tsirliganis, and N. A. Kazakis, “From Contemporary Datasets to Cultural Heritage Performance: Explainability and Energy Profiling of Visual Models Towards Textile Identification,” Heritage, vol. 8, no. 11, p. 447, Oct. 2025, doi: 10.3390/heritage8110447.

M. E. Prasetyo, M. R. Faza, R. Pratama, S. N. H. Alhabsy, H. Purwanti, and A. P. A. Masa, “Klasifikasi Ragam Kendaraan Menggunakan Metode Convolutional Neural Network (Cnn),” Adopsi Teknologi dan Sistem Informasi (ATASI), vol. 2, no. 2, pp. 142–148, Dec. 2023, doi: 10.30872/atasi.v2i2.1156.

J. E. Widyaya and S. Budi, “Pengaruh Preprocessing Terhadap Klasifikasi Diabetic Retinopathy dengan Pendekatan Transfer Learning Convolutional Neural Network,” Jurnal Teknik Informatika dan Sistem Informasi, vol. 7, no. 1, Apr. 2021, doi: 10.28932/jutisi.v7i1.3327.

R. D. Armelia, R. Andrian, and A. Junaidi, “Perbandingan Kinerja Backpropagation dan Convolutional Neural Network untuk Klasifikasi Citra Batik Lampung,” Jurnal Komputasi, vol. 12, no. 1, pp. 11–18, Apr. 2024, doi: 10.23960/komputasi.v12i1.248.

W. Musu, A. Ibrahim, and H. Heriadi, “Pengaruh Komposisi Data Training dan Testing terhadap Akurasi Algoritma C4.5,” SISITI : Seminar Ilmiah Sistem Informasi dan Teknologi Informasi, vol. 10, no. 1, pp. 186–195, Mar. 2021, doi: 10.36774/sisiti.v10i1.802.

B. Nugroho and E. Y. Puspaningrum, “Kinerja Metode CNN untuk Klasifikasi Pneumonia dengan Variasi Ukuran Citra Input,” Jurnal Teknologi Informasi dan Ilmu Komputer, vol. 8, no. 3, pp. 533–538, Jun. 2021, doi: 10.25126/jtiik.2021834515.

H. K. Putri, B. H. Iswanto, and H. Suhendar, “Klasifikasi Kualitas Cangkang Telur Ayam Menggunakan Efficientnet Berbasis Citra Digital,” Prosiding Seminar Nasional Fisika (E-Journal), vol. XIII, 2024, doi: 10.21009/03.1301.FA13.

A. M. Marhelio, M. Munir, and Y. Wihardi, “Klasifikasi Pose Kepala Siswa Menggunakan EfficientNetV2 dengan Seat Position Embedding,” JATISI (Jurnal Teknik Informatika dan Sistem Informasi), vol. 12, no. 3, Sep. 2025, doi: 10.35957/jatisi.v12i3.12987.

J. Krisna Putra and Y. Yoannita, “Transfer Learning dengan MobileNetV3 untuk Deteksi Serangan Spoofing Wajah pada Foto,” Jurnal Algoritme, vol. 5, no. 2, pp. 218–230, Apr. 2025, doi: 10.35957/algoritme.v5i2.10954.

M. N. M. Hakim, A. B. Nugroho, and A. E. Minarno, “Prediksi Tumor Otak Menggunakan Metode Convolutional Neural Network,” Informatika Mulawarman : Jurnal Ilmiah Ilmu Komputer, vol. 17, no. 1, p. 48, Jul. 2023, doi: 10.30872/jim.v17i1.5246.

A. Simarmata, A. Putra, and A. Husein, “Penerapan Metode Computer Vision Dalam Klasifikasi Buah Jeruk Menggunakan Teknik Image Pre-Processing,” Data Sciences Indonesia (DSI), vol. 3, no. 2, pp. 108–114, Jun. 2024, doi: 10.47709/dsi.v3i2.4010.

A. Akbar and D. I. Mulyana, “Optimasi Klasifikasi Batik Betawi Menggunakan Data Augmentasi Dengan Metode KNN Dan GLCM,” Jurnal Aplikasi Teknologi Informasi dan Manajemen (JATIM), vol. 3, no. 2, pp. 92–101, Nov. 2022, doi: 10.31102/jatim.v3i2.1577.

W. A. Kurniawan and A. Salam, “Penggunaan Feature Space SMOTE Untuk Mengurangi Overfitting Akibat Imbalance Dataset,” Jurnal Transformatika, vol. 22, no. 2, pp. 140–149, Jan. 2025, doi: 10.26623/transformatika.v22i2.8305.

Y. Amrozi, D. Yuliati, A. Susilo, N. Novianto, and R. Ramadhan, “Klasifikasi Jenis Buah Pisang Berdasarkan Citra Warna dengan Metode SVM,” Jurnal Sisfokom (Sistem Informasi dan Komputer), vol. 11, no. 3, pp. 394–399, Dec. 2022, doi: 10.32736/sisfokom.v11i3.1502.

N. J. Hayati, D. Singasatia, and M. R. Muttaqin, “Object Tracking Menggunakan Algoritma You Only Look Once (YOLO)v8 untuk Menghitung Kendaraan,” Komputa : Jurnal Ilmiah Komputer dan Informatika, vol. 12, no. 2, pp. 91–99, Nov. 2023, doi: 10.34010/komputa.v12i2.10654.

R. R. Adhitya, Wina Witanti, and Rezki Yuniarti, “PERBANDINGAN METODE CART DAN NAÏVE BAYES UNTUK KLASIFIKASI CUSTOMER CHURN,” INFOTECH journal, vol. 9, no. 2, pp. 307–318, Jul. 2023, doi: 10.31949/infotech.v9i2.5641.

J. Hartanto, S. M. Wijaya, Anderies, and A. Chowanda, “Performance Evaluation of EfficientNetB0, EfficientNetV2, and MobileNetV3 for American Sign Language Classification,” in ICEEIE 2023 - International Conference on Electrical, Electronics and Information Engineering, Institute of Electrical and Electronics Engineers Inc., 2023. doi: 10.1109/ICEEIE59078.2023.10334648.

D. P. Sidik, F. Utaminingrum, and L. Muflikhah, “Penggunaan Variasi Model pada Arsitektur EfficientNetV2 untuk Prediksi Sel Kanker Serviks,” J-PTIIK, vol. 7, no. 5, pp. 2116–2121, 2023, [Online]. Available: https://j-ptiik.ub.ac.id/index.php/j-ptiik/article/view/12656

K. Ma, S. Lee, X. Ma, and H. Chen, “Fine art image classification and design methods integrating lightweight deep learning,” Sci Rep, vol. 15, no. 1, p. 33006, Sep. 2025, doi: 10.1038/s41598-025-18420-0.