Studi Perbandingan Model Hybrid MobileNet-YOLO: Trade-off Akurasi dan Efisiensi Komputasi dalam Deteksi Objek
DOI:
https://doi.org/10.33884/comasiejournal.v14i01.11002Keywords:
Computational Efficiency, Hybrid Model, MobileNet, Object Detection, YOLOAbstract
Deploying object detection models on resource-constrained devices requires balancing high accuracy with computational efficiency. This research analyzes the performance trade-off of hybrid architectures combining MobileNet backbones (V2, V3-Small, and V3-Large) with YOLO detectors. The study employs an experimental method using the Pascal VOC dataset across four input resolutions ranging from 320 to 640 pixels to measure Mean Average Precision (mAP@50) and Frames Per Second (FPS). The results demonstrate a significant trade-off between precision and speed. MobileNetV3-Large at 640px achieves the highest accuracy of 58.5% mAP, making it suitable for precision-critical tasks. Conversely, MobileNetV3-Small at 320px proves to be the most efficient model, achieving 165.2 FPS on a GPU and maintaining real-time performance on a standard CPU at 30.4 FPS. These findings provide empirical guidance for selecting optimal hybrid architectures based on specific hardware constraints, proving that MobileNetV3-Small is the superior choice for low-power edge implementation.
References
Ashari, I., Negara, I. S. M., & A, A. S. S. (2025). Lightweight YOLO Models for Real-Time Multi-Vehicle Detection. Sinkron, 9(3), 1795–1810. https://doi.org/10.33395/sinkron.v9i3.15071
Jiang, H., Zhao, J., Ma, F., Yang, Y., & Yi, R. (2025). Mobile-YOLO: A Lightweight Object Detection Algorithm for Four Categories of Aquatic Organisms. Fishes, 10(7). https://doi.org/10.3390/fishes10070348
Khurana, K., Sonsare, P., Borkar, D., Thakkar, H., & Bhagat, O. (2025). MOLO: a hybrid approach using MobileNet and YOLO for object detection on resource constrained devices. Discover Artificial Intelligence, 5(1). https://doi.org/10.1007/s44163-025-00398-3
Nugroho, A. D., & Baihaqi, W. M. (2023). Improved YOLOv5 with Backbone Replacement to MobileNet V3s for School Attribute Detection. SinkrOn, 8(3), 1944–1954. https://doi.org/10.33395/sinkron.v8i3.12702
Ramdan, A., & Asriyanik, A. (2024). Implementasi Deteksi Objek Real-Time Sebagai Media Edukasi dengan Algoritma YOLOv8 pada Objek Sampah. Jurnal SAINTEKOM, 14(2), 142–153. https://doi.org/10.33020/saintekom.v14i2.638
Su, C., Zhu, L., Dai, W., Zhou, J., Wang, J., Mao, Y., & Sun, J. (2025). Nav-YOLO: A Lightweight and Efficient Object Detection Model for Real-Time Indoor Navigation on Mobile Platforms. ISPRS International Journal of Geo-Information, 14(9). https://doi.org/10.3390/ijgi14090364
Terven, J., Córdova-Esparza, D. M., & Romero-González, J. A. (2023). A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS. In Machine Learning and Knowledge Extraction (Vol. 5, Issue 4, pp. 1680–1716). Multidisciplinary Digital Publishing Institute (MDPI). https://doi.org/10.3390/make5040083
Wang, L., Wang, H., Letchmunan, S., Xiao, R., Ahmed, O. H., & Liu, Z. (2025). A systematic literature review of lightweight YOLO models for object detection. PeerJ Computer Science, 11, e3357. https://doi.org/10.7717/peerj-cs.3357
Zhang, J., Wang, J., & Zhao, M. (2023). A Lightweight Crop Pest Detection Algorithm Based on Improved Yolov5s. Agronomy, 13(7). https://doi.org/10.3390/agronomy13071779
Zhuang, F., Qi, Z., Duan, K., Xi, D., Zhu, Y., Zhu, H., Xiong, H., & He, Q. (2021). A Comprehensive Survey on Transfer Learning. In Proceedings of the IEEE (Vol. 109, Issue 1, pp. 43–76). Institute of Electrical and Electronics Engineers Inc. https://doi.org/10.1109/JPROC.2020.3004555
