Performance Analysis of Transfer Learning Models for Identifying AI-Generated and Real Images
Abstract
This study aims to analyze and compare the performance of three transfer learning methods, namely InceptionV3, VGG16, and DenseNet121, in detecting AI-generated and real images. The background of this research is the unknown performance of transfer learning methods for detecting AI-generated and real images. This study introduces innovation by conducting 54 experiments involving three types of transfer learning, three dataset split ratios (60:40, 70:30, and 80:20), three optimizers (Adam, SGD, and RMSprop), two numbers of epochs (20 and 50), and the addition of dense and flatten layers during fine tuning. Performance evaluation was conducted using binary cross entropy loss and confusion matrix. This research provides significant benefits in determining the most effective transfer learning model for detecting AI-generated and real images and offers practical guidance for further development. The results show that the InceptionV3 model with the Adam optimizer, an 80:20 split ratio, and 20 epochs achieved the highest accuracy of 84.26%, with a loss of 39.54%, precision of 81.33%, recall of 82.43%, and an F1-Score of 81.88%.
Full Text:
PDFReferences
D. Epstein, S. Jain, S. Wang, and Z. Zhang, “Online Detection of AI-Generated Images,” in Proc. ICCVW, 2023. [Online]. Available: https://openaccess.thecvf.com/content/ICCV2023W/DFAD/papers/Epstein_Online_Detection_of_AI-Generated_Images__ICCVW_2023_paper.pdf
S. S. Barahheem and T. V. Nguyen, “AI vs. AI: Can AI Detect AI-Generated Images?” [Online]. Available: https://www.researchgate.net/publication/374269358_AI_vs_AI_Can_AI_Detect_AI-Generated_Images
J. Gu et al., “AI-enabled image fraud in scientific publications,” J. Big Data, vol. 10, no. 1, pp. 1-12, 2022. [Online]. Available: https://www-sciencedirect-com.translate.goog/science/article/pii/S2666389922001039?_x_tr_sl=en&_x_tr_tl=id&_x_tr_hl=id&_x_tr_pto=tc
A. Peryanto, A. Yudhana, and R. Umar, “Rancang Bangun Klasifikasi Citra Dengan Teknologi Deep Learning Berbasis Metode Convolutional Neural Network,” in Proc. FORMAT, 2019, vol. 8, pp. 10-20. [Online]. Available: https://publikasi.mercubuana.ac.id/index.php/format/article/view/7849
Y. Zhou, X. Zhang, Y. Wang, and B. Zhang, “Transfer Learning and Its Application Research,” J. Phys. Conf. Ser., vol. 1920, no. 1, p. 012058, 2021. [Online]. Available: https://iopscience.iop.org/article/10.1088/1742-6596/1920/1/012058/pdf
M. Ahmed et al., “An inception V3 approach for malware classification using machine learning and transfer learning,” J. King Saud Univ. - Comput. Inf. Sci., vol. 34, no. 8, pp. 1-12, 2023. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S2666603022000252
A. M. Ibrahim et al., “Skin Cancer Classification Using Transfer Learning by VGG16 Architecture (Case Study on Kaggle Dataset),” Open Access Library Journal, vol. 10, pp. 1-12, 2023. [Online]. Available: https://www.scirp.org/journal/paperinformation?paperid=126855
J. Pardede and D. A. L. Putra, “Implementasi DenseNet Untuk Mengidentifikasi Kanker Kulit Melanoma,” JUTISI, vol. 8, no. 1, pp. 10-20, 2020. [Online]. Available: https://journal.maranatha.edu/index.php/jutisi/article/download/2814/1708/10108
C. Janiesch, P. Zschech, and K. Heinrich, “Machine learning and deep learning,” Bus. Inf. Syst. Eng., vol. 63, no. 3, pp. 303–314, 2021. [Online]. Available: https://link.springer.com/article/10.1007/s12525-021-00475-2
P. Purwono et al., “Understanding of Convolutional Neural Network (CNN): A Review,” IJRCS, vol. 1, no. 1, pp. 1-8, 2022. [Online]. Available: https://www.pubs2.ascee.org/index.php/IJRCS/article/view/888
A. Hosna et al., “Transfer learning: a friendly introduction,” J. Big Data, vol. 9, no. 1, pp. 1-21, 2022. [Online]. Available: https://journalofbigdata.springeropen.com/articles/10.1186/s40537-022-00652-w
U. Ungkawa and G. A. Hakim, “Klasifikasi Warna pada Kematangan Buah Kopi Kuning menggunakan Metode CNN Inception V3,” ELKOMIKA, vol. 11, no. 1, pp. 12-20, 2023. [Online]. Available: https://ejurnal.itenas.ac.id/index.php/elkomika/article/view/8899
W. W. Kusuma, R. R. Isnanto, and A. Fauzi, “Analisis Perbandingan Model CNN VGG16 Dan DenseNet121 Menggunakan Kerangka Kerja Tensorflow Untuk DeteksiI Jenis Hewan,” J. Teknol. Komput., vol. 8, no. 1, pp. 20-30, 2023. [Online]. Available: https://ejournal3.undip.ac.id/index.php/jtk/article/view/37009/28851
S. Montaha et al., “BreastNet18: A High Accuracy Fine-Tuned VGG16 Model Evaluated Using Ablation Study for Diagnosing Breast Cancer from Enhanced Mammography Images,” Biology, vol. 10, no. 12, p. 1347, 2021. [Online]. Available: https://www.mdpi.com/2079-7737/10/12/1347
M. A. Djohar et al., “Liver Segmentation Using Convolutional Neural Network Method with U-Net Architecture,” J. Inf. Technol. Electr., vol. 5, no. 2, pp. 1-8, 2022. [Online]. Available: https://ojs.uma.ac.id/index.php/jite/article/view/6751/4088
H. Shen et al., “Designing Alternative Representations of Confusion Matrices to Support Non-Expert Public Understanding of Algorithm Performance,” in Proc. 23rd ACM Conf. Comput. Interact. Sci. Pract., 2020, pp. 1-11. [Online]. Available: https://dl.acm.org/doi/abs/10.1145/3415224
S. Saponara and A. Elhanashi, “Impact of Image Resizing on Deep Learning Detectors for Training Time and Model Performance,” in Lecture Notes in Comput. Sci., vol. 12345, pp. 1-10, 2022. [Online]. Available: https://link.springer.com/chapter/10.1007/978-3-030-95498-7_2
Z. Pan et al., “Towards Bidirectional Arbitrary Image Rescaling: Joint Optimization and Cycle Idempotence,” in Proc. CVPR, 2022. [Online]. Available: https://openaccess.thecvf.com/content/CVPR2022/html/Pan_Towards_Bidirectional_Arbitrary_Image_Rescaling_Joint_Optimization_and_Cycle_Idempotence_CVPR_2022_paper.html
A. Racz, D. Bajusz, and K. Heberger, “Effect of Dataset Size and Train/Test Split Ratios in QSAR/QSPR Multiclass Classification,” Molecules, vol. 26, no. 4, p. 1111, 2021. [Online]. Available: https://www.mdpi.com/1420-3049/26/4/1111
K. Zhang, Z. Cao, and J. Wu, “Circular Shift: An Effective Data Augmentation Method For Convolutional Neural Network On Image Classification,” in Proc. 25th Int. Conf. Pattern Recognit., 2020, pp. 1-8. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/9191303
A. Abdelhamed et al., “NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Results,” in Proc. CVPRW, 2020, pp. 1-12. [Online]. Available: https://openaccess.thecvf.com/content_CVPRW_2020/html/w31/Abdelhamed_NTIRE_2020_Challenge_on_Real_Image_Denoising_Dataset_Methods_and_CVPRW_2020_paper.html
J. Sigut et al., “OpenCV Basics: A Mobile Application to Support the Teaching of Computer Vision Concepts,” in Proc. 2020 IEEE Global Eng. Educ. Conf., 2020, pp. 1-8. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/9103956
B. Raharjo, “Deep Learning dengan Python,” Yayasan Prima Agus Teknik, 2022. [Online]. Available: https://digilib.stekom.ac.id/assets/dokumen/ebook/feb_eab5a7c1f295129ba69a76fee4dff22266879314_1643796893.pdf
A. K. Reyes, J. C. Caicedo, and J. Camargo, “Fine-tuning Deep Convolutional Networks for Plant Recognition,” in Proc. 2019 IEEE Conf
DOI: https://doi.org/10.15408/jti.v17i2.40453 Abstract - 0 PDF - 0
Refbacks
- There are currently no refbacks.
Copyright (c) 2024 Arini Arini,Muhamad Azhari, Isnaieni Ijtima’ Amna Fitri,Feri Fahrianto
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
3rd Floor, Dept. of Informatics, Faculty of Science and Technology, UIN Syarif Hidayatullah Jakarta
Jl. Ir. H. Juanda No.95, Cempaka Putih, Ciputat Timur.
Kota Tangerang Selatan, Banten 15412
Tlp/Fax: +62 21 74019 25/ +62 749 3315
Handphone: +62 8128947537
E-mail: jurnal-ti@apps.uinjkt.ac.id
Jurnal Teknik Informatika by Prodi Teknik Informatika Universitas Islam Negeri Syarif Hidayatullah Jakarta is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Based on a work at http://journal.uinjkt.ac.id/index.php/ti.
JTI Visitor Counter: View JTI Stats