Real-Time Edge AI: Deploying Efficient Deep Learning Models for On-Device Inference

References

[1] H. Howard et al., 'Efficient CNN Architectures for Mobile Devices', IEEE TNNLS, 2019.

[2] A. Krizhevsky et al., 'ImageNet Classification with Deep CNNs', NIPS, 2012.

[3] M. Sandler et al., 'MobileNetV2: Inverted Residuals and Linear Bottlenecks', CVPR, 2018.

[4] F. Chollet, 'Xception: Deep Learning with Depthwise Separable Convolutions', CVPR, 2017.

[5] Y. Cheng et al., 'Model Compression and Acceleration for Deep Neural Networks', arXiv, 2017.

[6] H. Wang et al., "MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications," arXiv preprint arXiv:1704.04861, 2017.

[7] M. Tan and Q. Le, "EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks," arXiv:1905.11946, 2019.

[8] A. Krizhevsky, I. Sutskever, and G. Hinton, "ImageNet Classification with Deep Convolutional Neural Networks," NIPS, 2012.

[9] K. He et al., "Deep Residual Learning for Image Recognition," CVPR, 2016.

[10] Y. LeCun et al., "Gradient-Based Learning Applied to Document Recognition," Proceedings of the IEEE, 1998.

[11] Mohit Jain and Adit Shah (2021). Convolutional neural networks for real-time object detection with raspberry Pi. https://wjaets.com/sites/default/files/WJAETS2021-0067.pdf. https://doi.org/10.30574/wjaets.2021.4.1.0067

[12] S. Ioffe and C. Szegedy, "Batch Normalization: Accelerating Deep Network Training," ICML, 2015.

[13] F. Chollet, "Xception: Deep Learning with Depthwise Separable Convolutions," CVPR, 2017.

[14] D. Howard et al., "Searching for MobileNetV3," ICCV, 2019.

[15] Nair and G. Hinton, "Rectified Linear Units Improve Restricted Boltzmann Machines," ICML, 2010.

[16] M. Sandler et al., "MobileNetV2: Inverted Residuals and Linear Bottlenecks," CVPR, 2018.

[17] J. Redmon et al., "You Only Look Once: Unified, Real-Time Object Detection," CVPR, 2016.

[18] J. Deng et al., "ImageNet: A Large-Scale Hierarchical Image Database," CVPR, 2009.

[19] C. Szegedy et al., "Going Deeper with Convolutions," CVPR, 2015.

[20] M. Abadi et al., "TensorFlow: A System for Large-Scale Machine Learning," OSDI, 2016.

[21] A. Paszke et al., "PyTorch: An Imperative Style, High-Performance Deep Learning Library," NeurIPS, 2019.

[22] H. Han et al., "The Edge of Intelligence: A Survey on Edge AI," IEEE Access, 2019.

[23] A. Graves et al., "Speech Recognition with Deep Recurrent Neural Networks," ICASSP, 2013.

[24] Y. Gal and Z. Ghahramani, "Dropout as a Bayesian Approximation," ICML, 2016.

[25] R. Girshick, "Fast R-CNN," ICCV, 2015.

[26] S. Ren et al., "Faster R-CNN: Towards Real-Time Object Detection," NIPS, 2015.

[27] X. Glorot and Y. Bengio, "Understanding the Difficulty of Training Deep Feedforward Networks," AISTATS, 2010.

[28] J. Ba and R. Caruana, "Do Deep Nets Really Need to be Deep?," NIPS, 2014.

[29] Mohit Jain and Adit Shah (2021). Convolutional neural networks for real-time object detection with raspberry Pi. https://wjaets.com/sites/default/files/WJAETS2021-0067.pdf. https://doi.org/10.30574/wjaets.2021.4.1.0067

[30] G. Hinton et al., "Distilling the Knowledge in a Neural Network," arXiv:1503.02531, 2015.

[31] B. Zoph and Q. Le, "Neural Architecture Search with Reinforcement Learning," ICLR, 2017.

[32] Y. Wu and K. He, "Group Normalization," ECCV, 2018.

@article{1709741,
      author = {Luis Madrigal, Ofer Ronen, Leon Chlon},
      title = {Real-Time Edge AI: Deploying Efficient Deep Learning Models for On-Device Inference},
      journal = {Iconic Research And Engineering Journals},
      year = {2023},
      volume = {6},
      number = {12},
      pages = {1619-1622},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1709741.pdf},
      abstract = {Edge AI is transforming the landscape of smart devices by enabling real-time inference on resource-constrained hardware. This paper presents a framework for deploying lightweight deep learning models that strike a balance between accuracy and latency.},
      month = {June},
  }