{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T02:31:31Z","timestamp":1760236291675,"version":"build-2065373602"},"reference-count":42,"publisher":"MDPI AG","issue":"22","license":[{"start":{"date-parts":[[2021,11,12]],"date-time":"2021-11-12T00:00:00Z","timestamp":1636675200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The demand for object detection capability in edge computing systems has surged. As such, the need for lightweight Convolutional Neural Network (CNN)-based object detection models has become a focal point. Current models are large in memory and deployment in edge devices is demanding. This shows that the models need to be optimized for the hardware without performance degradation. There exist several model compression methods; however, determining the most efficient method is of major concern. Our goal was to rank the performance of these methods using our application as a case study. We aimed to develop a real-time vehicle tracking system for cargo ships. To address this, we developed a weighted score-based ranking scheme that utilizes the model performance metrics. We demonstrated the effectiveness of this method by applying it on the baseline, compressed, and micro-CNN models trained on our dataset. The result showed that quantization is the most efficient compression method for the application, having the highest rank, with an average weighted score of 9.00, followed by binarization, having an average weighted score of 8.07. Our proposed method is extendable and can be used as a framework for the selection of suitable model compression methods for edge devices in different applications.<\/jats:p>","DOI":"10.3390\/s21227529","type":"journal-article","created":{"date-parts":[[2021,11,14]],"date-time":"2021-11-14T20:51:53Z","timestamp":1636923113000},"page":"7529","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Evaluation of Deep Neural Network Compression Methods for Edge Devices Using Weighted Score-Based Ranking Scheme"],"prefix":"10.3390","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4863-5422","authenticated-orcid":false,"given":"Olutosin Ajibola","family":"Ademola","sequence":"first","affiliation":[{"name":"Embedded AI Research Laboratory, Department of Computer Systems, Tallinn University of Technology, Ehitajate tee 5, 19086 Tallinn, Estonia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9878-4477","authenticated-orcid":false,"given":"Mairo","family":"Leier","sequence":"additional","affiliation":[{"name":"Embedded AI Research Laboratory, Department of Computer Systems, Tallinn University of Technology, Ehitajate tee 5, 19086 Tallinn, Estonia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2167-6280","authenticated-orcid":false,"given":"Eduard","family":"Petlenkov","sequence":"additional","affiliation":[{"name":"Centre for Intelligent Systems, Department of Computer Systems, Tallinn University of Technology, Ehitajate tee 5, 19086 Tallinn, Estonia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2021,11,12]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TNNLS.2019.2933467","article-title":"Object detection with deep learning: A review","volume":"1","author":"Zhao","year":"2019","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014, January 23\u201328). Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Liu, S., and Deng, W. (2015, January 3\u20136). Very deep convolutional neural network-based image classification using small training sample size. Proceedings of the 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR), Kuala Lumpur, Malaysia.","DOI":"10.1109\/ACPR.2015.7486599"},{"key":"ref_5","unstructured":"Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., and Keutzer, K. (2016). Squeezenet: Alexnet-level accuracy with 50x fewer parameters and less than 0.5 mb model size. arXiv."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, X., Lin, M., and Sun, J. (2017). Shufflenet: An extremely efficient convolutional neural network for mobile devices. arXiv.","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref_7","unstructured":"Tan, M., and Le, Q.V. (2020). Efficientnet: Rethinking model scaling for convolutional neural networks. arXiv."},{"key":"ref_8","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2014, January 7\u201312). Going deeper with convolutions. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref_10","unstructured":"Cheng, Y., Wang, D., Zhou, P., and Zhang, T. (2017). A survey of model compression and acceleration for deep neural networks. arXiv."},{"key":"ref_11","unstructured":"Courbariaux, M., Hubara, I., Soudry, D., El-Yaniv, R., and Bengio, Y. (2016). Binarized neural networks: Training deep neural networks with weights and activations constrained to +1 or -1. arXiv."},{"key":"ref_12","unstructured":"Courbariaux, M., Bengio, Y., and David, J.-P. (2016, January 7\u201312). Binaryconnect: Training deep neural networks with binary weights during propagations. Proceedings of the 28th International Conference on Neural Information Processing Systems, Montreal, QC, Canada."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Nahshan, Y., Chmiel, B., Baskin, C., Zheltonozhskii, E., Banner, R., Bronstein, A.M., and Mendelson, A. (2020). Loss aware post-training quantization. arXiv.","DOI":"10.1007\/s10994-021-06053-z"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2020\/7839064","article-title":"A novel low-bit quantization strategy for compressing deep neural networks","volume":"2","author":"Long","year":"2020","journal-title":"Comput. Intell. Neurosci."},{"key":"ref_15","unstructured":"Deng, X., and Zhang, Z. (2020). An embarrassingly simple approach to training ternary weight networks. arXiv."},{"key":"ref_16","unstructured":"Shayer, O., Levi, D., and Fetaya, E. (2018). Learning discrete weights using the local reparameterization trick. arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Rastegari, M., Ordonez, V., Redmon, J., and Farhadi, A. (2016). Xnor-Net: Imagenet Classification Using Binary Convolutional Neural Networks, Springer.","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Moosavi-Dezfooli, S.-M., Cheung, N.-M., and Frossard, P. (2017). Adaptive quantization for deep neural network. arXiv.","DOI":"10.1609\/aaai.v32i1.11623"},{"key":"ref_19","unstructured":"Stock, P., Joulin, A., Gribonval, R., Graham, B., and Jegou, H. (2020). And the bit goes down: Revisiting the quantization of neural networks. arXiv."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Buciluundefined, C., Caruana, R., and Niculescu-Mizil, A. (2006, January 20\u201323). Model compression. Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Ser. KDD\u201906, New York, NY, USA.","DOI":"10.1145\/1150402.1150464"},{"key":"ref_21","unstructured":"Hinton, G., Vinyals, O., and Dean, J. (2015). Distilling the knowledge in a neural network. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Cho, J.H., and Hariharan, B. (November, January 27). On the efficacy of knowledge distillation. Proceedings of the 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), Seoul, Korea.","DOI":"10.1109\/ICCV.2019.00489"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Lu, Y., Kumar, A., Zhai, S., Cheng, Y., Javidi, T., and Feris, R. (2016, January 21\u201326). Fullyadaptive feature sharing in multi-task networks with applications in person attribute classification. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.126"},{"key":"ref_24","unstructured":"Denton, E., Zaremba, W., Bruna, J., LeCun, Y., and Fergus, R. (2014, January 8\u201313). Exploiting linear structure within convolutional networks for efficient evaluation. Proceedings of the 27th International Conference on Neural Information Processing Systems\u2014Volume 1 (NIPS\u201914), Montreal, QC, Canada."},{"key":"ref_25","unstructured":"Kholiavchenko, M. (2020). Iterative low-rank approximation for CNN compression. arXiv."},{"key":"ref_26","unstructured":"Sankararaman, K.A., De, S., Xu, Z., Huang, W.R., and Goldstein, T. (2020). The impact of neural network overparameterization on gradient confusion and stochastic gradient descent. arXiv."},{"key":"ref_27","unstructured":"Huynh, T.Q., and Setiono, R. (August, January 31). Effective neural network pruning using cross-validation. Proceedings of the 2005 IEEE International Joint Conference on Neural Networks, Montreal, QC, Canada."},{"key":"ref_28","unstructured":"Ding, X., Ding, G., Zhou, X., Guo, Y., Han, J., and Liu, J. (2019). Global sparse momentum sgd for pruning very deep neural networks. arXiv."},{"key":"ref_29","unstructured":"Han, S., Pool, J., Tran, J., and Dally, W.J. (2015, January 7\u201312). Learning both weights and connections for efficient neural networks. Proceedings of the 28th International Conference on Neural Information Processing Systems, Montreal, QC, Canada."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1109\/72.248452","article-title":"Pruning algorithms\u2014A survey","volume":"4","author":"Reed","year":"1993","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"2273","DOI":"10.1109\/ACCESS.2018.2886876","article-title":"Prune deep neural networks with the modified l1\/2 penalty","volume":"7","author":"Chang","year":"2019","journal-title":"IEEE Access"},{"key":"ref_32","unstructured":"Mozer, M.C., and Smolensky, P. (1988). Skeletonization: A technique for trimming the fat from a network via relevance assessment. Proceedings of the 1st International Conference on Neural Information Processing Systems, Ser. NIPS\u201988, MIT Press."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1007\/s11063-011-9196-7","article-title":"A novel pruning algorithm for optimizing feedforward neural network of classification problems","volume":"34","author":"Augasta","year":"2011","journal-title":"Neural Process. Lett."},{"key":"ref_34","unstructured":"Simonyan, K., and Zisserman, A. (2016). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2015, January 27\u201330). Rethinking the inception architecture for computer vision. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., and Alemi, A. (2016). Inception-v4, inception-resnet and the impact of residual connections on learning. arXiv.","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Barry, D., Shah, M., Keijsers, M., Khan, H., and Hopman, B. (2019). xyolo: A model for real-time object detection in humanoid soccer on low-end hardware. arXiv.","DOI":"10.1109\/IVCNZ48456.2019.8960963"},{"key":"ref_38","unstructured":"Chollet, F. (2021, July 14). Keras. Available online: https:\/\/github.com\/fchollet\/keras."},{"key":"ref_39","unstructured":"Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., and Devin, M. (2021, July 14). TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. Available online: tensorflow.org."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1746","DOI":"10.21105\/joss.01746","article-title":"Larq: An open-source library for training binarized neural networks","volume":"5","author":"Geiger","year":"2020","journal-title":"J. Open Source Softw."},{"key":"ref_41","first-page":"1","article-title":"Tensor train decomposition on tensorflow (t3f)","volume":"21","author":"Novikov","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref_42","unstructured":"(2021, September 30). Google Coral Products Page. Available online: https:\/\/coral.ai\/docs\/dev-board\/datasheet\/."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/22\/7529\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:29:31Z","timestamp":1760167771000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/22\/7529"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,12]]},"references-count":42,"journal-issue":{"issue":"22","published-online":{"date-parts":[[2021,11]]}},"alternative-id":["s21227529"],"URL":"https:\/\/doi.org\/10.3390\/s21227529","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2021,11,12]]}}}