An Evaluation of Neural Network Efficacies for Image Recognition on Edge-AI Computer Vision Platform

Authors: Jie Zhao, Meng Su

Abstract:

Image recognition enables machine-like robotics to understand a scene and plays an important role in computer vision applications. Computer vision platforms as physical infrastructure, supporting Neural Networks for image recognition, are deterministic to leverage the performance of different Neural Networks. In this paper, three different computer vision platforms – edge AI (Jetson Nano, with 4GB), a standalone laptop (with RTX 3000s, using CUDA), and a web-based device (Google Colab, using GPU) are investigated. In the case study, four prominent neural network architectures (including AlexNet, VGG16, GoogleNet, and ResNet (34/50)), are deployed. By using public ImageNets (Cifar-10), our findings provide a nuanced perspective on optimizing image recognition tasks across Edge-AI platforms, offering guidance on selecting appropriate neural network structures to maximize performance under hardware constraints.

Keywords: AlexNet, VGG, GoogleNet, ResNet, ImageNet, Cifar-10, Edge AI, Jetson Nano, CUDA, GPU.

References:

[1] Y. H. Lu et al. “Rebooting Computing and Low-Power Image Recognition Challenge”. In: IEEE/ACM International Conference on Computer-Aided Design. 2015, pp. 927–932.
[2] K. Gauen et al., “Low-power image recognition challenge,” in Proceedings of ASP-DAC, IEEE, 2017, pp. 99–104.
[3] D. Kang, D. Kang, J. Kang, S. Yoo, and S. Ha, “Joint optimization of speed, accuracy, and energy for embedded image recognition systems,” in 2018 Design, Automation Test in Europe Conference Exhibition (DATE), March 2018, pp. 715–720.
[4] Y Shi, H Li, “Beyond cross-view image retrieval: Highly accurate vehicle localization using satellite image”, in Proceedings of the IEEE/CVF 2022
[5] H Yu, Y Luo, M Shu, Y Huo, Z Yang, Y Shi, Z Guo, H Li, X Hu, J Yuan, Z Nie, “Dair-v2x: A large-scale dataset for vehicle-infrastructure cooperative 3d object detection”, in Proceedings of the IEEE/CVF, 2022
[6] YJ Li, J Park, M O'Toole, “Modality-agnostic learning for radar-lidar fusion in vehicle detection”, in Proceedings of the IEEE/CVF, 2022
[7] M Bahari, S Saadatnejad, A Rahimi, M Shaverdikondori, AH Shahidzadeh, “Vehicle trajectory prediction works, but not everywhere”, in Proceedings of the IEEE/CVF, 2022
[8] R Xu, X Xia, J Li, H Li, S Zhang, Z Tu, “V2v4real: A real-world large-scale dataset for vehicle-to-vehicle cooperative perception”, in Proceedings of the IEEE/CVF, 2023
[9] H Yu, W Yang, H Ruan, Z Yang, Y Tang, X Gao, X Hao, Y Shi, Y Pan, N Sun, J Song, J Yuan, “V2X-Seq: A Large-Scale Sequential Dataset for Vehicle-Infrastructure Cooperative Perception and Forecasting”, in Proceedings of the IEEE/CVF, 2023
[10] Y LeCun, B Boser, JS Denker, D Henderson, “Backpropagation applied to handwritten zip code recognition”, in Proceedings of the IEEE, 1989
[11] Y LeCun, L Bottou, Y Bengio, “Gradient-based learning applied to document recognition”, in Proceedings of the IEEE, 1998
[12] A Krizhevsky, I Sutskever, “Imagenet classification with deep convolutional neural networks”, in NIPS, 2012
[13] K Simonyan, A Zisserman, “Very deep convnets for large-scale image recognition”, in ICLR, 2014
[14] C Szegedy, W Liu, Y Jia, P Sermanet, “Going deeper with convolutions”, in CVPR, 2015
[15] K He, X Zhang, S Ren, J Sun, “Deep Residual Learning for Image Recognition”, in CVPR, 2016
[16] J Deng, W Dong, R Socher, LJ Li, K Li, “Imagenet: A large-scale hierarchical image database”, in CVPR, 2009
[17] Li Deng, “The mnist database of handwritten digit images for machine learning research”, in IEEE Signal Processing Magazine, Volume: 29 Issue: 6, 2012
[18] Casper Solheim Bojer, Jens Peder Meldgaard, “Kaggle forecasting competitions: An overlooked learning opportunity”, in International Journal of Forecasting, Volume 37, Issue 2, Pages 587-603, 2021
[19] V Thakkar, S Tewary, “Batch Normalization in Convolutional Neural Networks—A comparative study with CIFAR-10 data”, in EAIT, 2018
[20] Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, Alexander C. Berg & Li Fei-Fei, “ImageNet Large Scale Visual Recognition Challenge”, in International Journal of Computer Vision, Volume 115, pages 211–252, 2015
[21] M Everingham, L Van Gool, CKI Williams, J Winn, A Zisserman, “The Pascal Visual Object Classes (VOC) Challenge”, International Journal of Computer Vision, Volume 88, pages 303–338, 2010
[22] Girshick, Ross, et al. "Rich feature hierarchies for accurate object detection and semantic segmentation." Proceedings of the IEEE conference on computer vision and pattern recognition. 2014.
[23] NVIDIA Jetson Nano Developer Kit: https://developer.nvidia.com/embedded/learn/get-started-jetson-nano-devkit
[24] Ekaba Bisong, “Building Machine Learning and Deep Learning Models on Google Cloud Platform”, ISBN- 978-1484244692, Springer, 2019
[25] Sebastian Raschka, Vahid Mirjalili, “Python Machine Learning: Machine Learning and Deep Learning with Python, scikit-learn, and TensorFlow”, ISBN- 978-1789955750, Packt Publishing, 2019
[26] Sebastian Raschka, Yuxi (Hayden) Liu, “Machine Learning with PyTorch and Scikit-Learn: Develop machine learning and deep learning models with Python”, ISBN- 978-1801819312, Packt Publishing, 2022
[27] Sebastian Raschka, David Julian, “Python: Deeper Insights into Machine Learning: Leverage benefits of machine learning techniques using Python”, ISBN- 978-1787128576, Pack Publishing, 2016