A First Look at Deep Learning Apps on Smartphones
arXiv:1812.05448
Abstract
We are in the dawn of deep learning explosion for smartphones. To bridge the gap between research and practice, we present the first empirical study on 16,500 the most popular Android apps, demystifying how smartphone apps exploit deep learning in the wild. To this end, we build a new static tool that dissects apps and analyzes their deep learning functions. Our study answers threefold questions: what are the early adopter apps of deep learning, what do they use deep learning for, and how do their deep learning models look like. Our study has strong implications for app developers, smartphone vendors, and deep learning R\&D. On one hand, our findings paint a promising picture of deep learning for smartphones, showing the prosperity of mobile deep learning frameworks as well as the prosperity of apps building their cores atop deep learning. On the other hand, our findings urge optimizations on deep learning models deployed on smartphones, the protection of these models, and validation of research ideas on these models.
References in corpus (10)
- Distilling the Knowledge in a Neural Network
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
- MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
- Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
- Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware
- Bayesian Dark Knowledge
- A Berkeley View of Systems Challenges for AI
- Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring