Comparison of ResNet50V2 and InceptionV3 with Adam, SGD, RMSprop Optimizers for Road Image Classification
Keywords:
Adam Optimizer, Convolutional Neural Network, Image Classification, ResNet50V2, Road Condition ClassificationAbstract
This study compares two Convolutional Neural Network (CNN) architectures ResNet50V2 and InceptionV3 with three optimizers (Adam, RMSprop, and SGD) for road condition classification. Using a dataset of 1,000 images categorized into four classes, the models were evaluated based on accuracy, precision, recall, and F1-score. Based on the results, ResNet50V2 with Adam optimizer performed the best, achieving 99% accuracy, whereas SGD yielded less-than-ideal results. This study is interesting since it compares architecture–optimizer pairings, a topic that hasn't been extensively studied in other studies. The results offer useful information for creating automated and dependable road monitoring systems that facilitate effective infrastructure upkeep. To further enhance performance, future study might entail implementing regularization techniques and growing the dataset.
References
A. Paramarthalingam, J. Sivaraman, and P. Theerthagiri, “A deep learning model to assist visually impaired in pothole detection using computer vision,” Decis. Anal. J., vol. 12, no. August, p. 100507, 2024, doi: 10.1016/j.dajour.2024.100507.
S. Swain and A. K. Tripathy, “Automatic detection of potholes using VGG-16 pre-trained network and Convolutional Neural Network,” Heliyon, vol. 10, no. 10, p. e30957, 2024, doi: 10.1016/j.heliyon.2024.e30957.
B. Omarov and B. Kulambayev, “ScienceDirect ScienceDirect Deep Learning-Based Image Processing for Real-Time Detection of Deep Learning-Based Image Processing for Real-Time Detection of Road Surface Damage Road Surface Damage,” Procedia Comput. Sci., vol. 251, no. 2023, pp. 609–614, 2024, doi: 10.1016/j.procs.2024.11.157.
D. Li, Z. Duan, X. Hu, D. Zhang, and Y. Zhang, “Automated classification and detection of multiple pavement distress images based on deep learning,” J. Traffic Transp. Eng. (English Ed., vol. 10, no. 2, pp. 276–290, 2023, doi: 10.1016/j.jtte.2021.04.008.
H. Song, K. Baek, and Y. Byun, “Pothole Detection using Machine Learning,” no. February, pp. 151–155, 2018, doi: 10.14257/astl.2018.150.35.
P. D. Rinanda, D. N. Aini, T. A. Pertiwi, S. Suryani, and A. J. Prakash, “Implementation of Convolutional Neural Network (CNN) for Image Classification of Leaf Disease In Mango Plants Using Deep Learning Approach,” Public Res. J. Eng. Data Technol. Comput. Sci., vol. 1, no. 2, pp. 56–61, 2024, doi: 10.57152/predatecs.v1i2.872.
D. Lestari, A. Mulya, A. Tatamara, R. R. Haiban, and H. D. Khalifah, “Deep Learning for Pneumonia Detection in Chest X-Rays using Different Algorithms and Transfer Learning Architectures,” Public Res. J. Eng. Data Technol. Comput. Sci., vol. 3, no. 1, pp. 10–21, 2025.
V. Wulandari, W. J. Sari, Z. H. Al-sawaff, and S. Manickam, “Comparative Analysis of Weather Image Classification Using CNN Algorithm with InceptionV3, DenseNet169 and NASNetMobile Architecture Models,” Inst. Res. Publ. Indones., vol. 2, no. January, pp. 81–92, 2025, doi: https://doi.org/10.57152/predatecs.v2i2.1609.
C. Saisree and U. Kumaran, “Pothole Detection Using Deep Learning Classification Method,” Procedia Comput. Sci., vol. 218, pp. 2143–2152, 2022, doi: 10.1016/j.procs.2023.01.190.
C. Lin and Y. Liu, “Research on Potholes Detection Based on Improved Mask RCNN Algorithms”.
G. Parasnis, A. Chokshi, V. Jain, and K. Devadkar, “RoadScan: A Novel and Robust Transfer Learning Framework for Autonomous Pothole Detection in Roads,” 2023 IEEE 7th Conf. Inf. Commun. Technol. CICT 2023, 2023, doi: 10.1109/CICT59886.2023.10455143.
S. Dutta, “International Journal of Scientific Research and Reviews,” Int. J. Sci. Res. Rev., vol. 8, no. 2, pp. 2475–2483, 2019.
R. K. Ibrahim, R. Mustapha, and K. Haruna, “Enhanced Deep learning for Pothole Detection in Autonomous Vehicles .,” vol. 1, no. 1, pp. 91–100, 2024.
D. Anggara, N. Suarna, and Y. Arie Wijaya, “Performance Comparison Analysis Of Optimizer Adam, SGD, and RMSPROP on The H5 Model,” J. Ilm. NERO, vol. 8, no. 1, p. 2023, 2023.
H. Maeda, Y. Sekimoto, T. Seto, T. Kashiyama, and H. Omata, “Road Damage Detection and Classification Using Deep Neural Networks with Smartphone Images,” Comput. Civ. Infrastruct. Eng., vol. 33, no. 12, pp. 1127–1141, 2018, doi: 10.1111/mice.12387.
D. Arya, H. Maeda, S. K. Ghosh, D. Toshniwal, and Y. Sekimoto, “RDD2022: A multi?national image dataset for automatic road damage detection - Arya - Geoscience Data Journal - Wiley Online Library.” pp. 846–862, 2023. doi: 10.1002/gdj3.260.
M. Fasounaki, E. B. Yüce, S. Öncül, and G. Ince, “CNN-based Text-independent Automatic Speaker Identification Using Short Utterances,” Proc. - 6th Int. Conf. Comput. Sci. Eng. UBMK 2021, vol. 01, pp. 413–418, 2021, doi: 10.1109/UBMK52708.2021.9559031.
S. S. Sulaiman, I. Nadher, and S. M. Hameed, “Credit Card Fraud Detection Using Improved Deep Learning Models,” Comput. Mater. Contin., vol. 78, no. 1, pp. 1049–1069, 2024, doi: 10.32604/cmc.2023.046051.
M. Tavakoli, R. Chandra, F. Tian, and C. Bravo, “Multi-modal deep learning for credit rating prediction using text and numerical data streams,” Appl. Soft Comput., vol. 171, no. October 2024, p. 112771, 2025, doi: 10.1016/j.asoc.2025.112771.
S. Hong, Y. Zhou, J. Shang, C. Xiao, and J. Sun, “Opportunities and challenges of deep learning methods for electrocardiogram data: A systematic review,” Comput. Biol. Med., vol. 122, 2020, doi: 10.1016/j.compbiomed.2020.103801.
Verdy and Ery Hartati, “Klasifikasi Penyakit Mata Menggunakan Convolutional Neural Network Model Resnet-50,” J. Rekayasa Sist. Inf. dan Teknol., vol. 1, no. 3, pp. 199–206, 2024, doi: 10.59407/jrsit.v1i3.529.
A. Zalvadila, “Klasifikasi Penyakit Tanaman Bawang Merah Menggunakan Metode SVM dan CNN,” J. Inform. J. Pengemb. IT, vol. 8, no. 3, pp. 255–260, 2023, doi: 10.30591/jpit.v8i3.5341.
D. Iswantoro and D. Handayani UN, “Klasifikasi Penyakit Tanaman Jagung Menggunakan Metode Convolutional Neural Network (CNN),” J. Ilm. Univ. Batanghari Jambi, vol. 22, no. 2, p. 900, 2022, doi: 10.33087/jiubj.v22i2.2065.
S. Dewi, F. Ramadhani, and S. Djasmayena, “Klasifikasi Jenis Jerawat Berdasarkan Gambar Menggunakan Algoritma CNN (Convolutional Neural Network),” Hello World J. Ilmu Komput., vol. 3, no. 2, pp. 68–73, 2024, doi: 10.56211/helloworld.v3i2.518.
J. Alberto and D. Hermanto, “Klasifikasi Jenis Burung Menggunakan Metode CNN ResNet-50 [1],” J. Tek. Inform. dan Sist. Inf., vol. 10, no. 3, pp. 34–36, 2023.
M. L. Septipalan, M. S. Hibrizi, N. Latifah, R. Lina, and F. Bimantoro, “Klasifikasi Tumor Otak Menggunakan CNN Dengan Arsitektur Resnet50,” Semin. Nas. Teknol. Sains, vol. 3, no. 1, pp. 103–108, 2024, doi: 10.29407/stains.v3i1.4357.
J. Algoritme et al., “Pengenalan Motif Songket Palembang Menggunakan Convolutional Neural Network dengan Arsitektur ResNet-50,” vol. 5, no. 1, pp. 78–87, 2024, doi: 10.35957/algoritme.xxxx.
E. Andreas and W. Widhiarso, “Klasifikasi Penyakit Mata Katarak Menggunakan Convolutional Neural Network Dengan Arsitektur Inception V3,” MDP Student Conf., vol. 2, no. 1, pp. 107–113, 2023, doi: 10.35957/mdp-sc.v2i1.3660.
K. Zairan Maulana and A. Susanto, “Implementasi Arsitektur CNN Inception V3 untuk Identifikasi Spesies Burung Endemik di Indonesia,” J. Pustaka Robot Sister (Jurnal Pus. Akses Kaji. Robot. Sist. Tertanam, dan Sist. Terdistribusi), vol. 2, no. 1, pp. 22–27, 2024, doi: 10.55382/jurnalpustakarobotsister.v2i1.775.
U. UNGKAWA and G. AL HAKIM, “Klasifikasi Warna pada Kematangan Buah Kopi Kuning menggunakan Metode CNN Inception V3,” ELKOMIKA J. Tek. Energi Elektr. Tek. Telekomun. Tek. Elektron., vol. 11, no. 3, p. 731, 2023, doi: 10.26760/elkomika.v11i3.731.
D. Soydaner, “A Comparison of Optimization Algorithms for Deep Learning,” Int. J. Pattern Recognit. Artif. Intell., vol. 34, no. 13, 2020, doi: 10.1142/S0218001420520138.
I. Chakroun, T. Haber, and T. J. Ashby, “SW-SGD: The Sliding Window Stochastic Gradient Descent Algorithm,” Procedia Comput. Sci., vol. 108, pp. 2318–2322, 2017, doi: 10.1016/j.procs.2017.05.082.
B. Soujanya and T. Sitamahalakshmi, “Optimization with ADAM and RMSprop in Convolution neural Network (CNN): A Case study for Telugu Handwritten Characters,” Int. J. Emerg. Trends Eng. Res., vol. 8, no. 9, pp. 5116–5121, 2020, doi: 10.30534/ijeter/2020/38892020.
A. Pasha et al., “Leveraging ANFIS with Adam and PSO optimizers for Parkinson’s disease,” Heliyon, vol. 10, no. 9, p. e30241, 2024, doi: 10.1016/j.heliyon.2024.e30241.
L. Yang, “Theoretical Analysis of Adam Optimizer in the Presence of Gradient Skewness,” vol. 7, no. 2, pp. 27–42, 2024.
K. Penyakit, D. Anggur, W. Rohman, N. Rifa, D. Erwanto, and I. Yanuartanti, “Evaluasi Kinerja CNN dengan Optimizer RMSprop , Adam dan,” pp. 91–104.
P. R. Kiran and N. C. Naveen, “Op-RMSprop (Optimized-Root Mean Square Propagation) Classification for Prediction of Polycystic Ovary Syndrome (PCOS) using Hybrid Machine Learning Technique,” Int. J. Adv. Comput. Sci. Appl., vol. 13, no. 6, pp. 588–596, 2022, doi: 10.14569/IJACSA.2022.0130671.
