paper-with-me

홈 › Papers

AI Benchmark: Running Deep Neural Networks on Android Smartphones

2018-10-02 · Andrey Ignatov, Radu Timofte, William Chou, Ke Wang, Max Wu, Tim Hartley, Luc van Gool

Over the last years, the computational power of mobile devices such as smartphones and tablets has grown dramatically, reaching the level of desktop computers available not long ago. While standard smartphone apps are no longer a problem for them, there is still a group of tasks that can easily challenge even high-end devices, namely running artificial intelligence algorithms. In this paper, we present a study of the current state of deep learning in the Android ecosystem and describe available frameworks, programming models and the limitations of running AI on smartphones. We give an overview of the hardware acceleration resources available on four main mobile chipset platforms: Qualcomm, HiSilicon, MediaTek and Samsung. Additionally, we present the real-world performance results of different mobile SoCs collected with AI Benchmark that are covering all main existing hardware configurations.

📄 PDF Abstract BibTeX arXiv:1810.01109

Code (1)

Video-Streaming-Pipeline/Video-Streaming-Pipeline

Similar Papers 제목 키워드 기반

Sub-millisecond Video Synchronization of Multiple Android Smartphones

2021-07-02 · Azat Akhmetyanov, Anastasiia Kornilova, Marsel Faizullin, David Pozo 외

This paper addresses the problem of building an affordable easy-to-setup synchronized multi-view camera system, which is in demand for many Computer Vision and Robotics applications in high-dynamic environments. In our w…

Video Synchronization

CNNdroid: GPU-Accelerated Execution of Trained Deep Convolutional Neural Networks on Android

2015-11-23 · Seyyed Salar Latifi Oskouei, Hossein Golestani, Matin Hashemi, Soheil Ghiasi

Many mobile applications running on smartphones and wearable devices would potentially benefit from the accuracy and scalability of deep CNN-based machine learning algorithms. However, performance and energy consumption …

BIG-bench Machine LearningGPU

Association Rule Based Flexible Machine Learning Module for Embedded System Platforms like Android

2014-11-14 · Amiraj Dhawan, Shruti Bhave, Amrita Aurora, Vishwanathan Iyer

The past few years have seen a tremendous growth in the popularity of smartphones. As newer features continue to be added to smartphones to increase their utility, their significance will only increase in future. Combini…

BIG-bench Machine Learning

SlimLM: An Efficient Small Language Model for On-Device Document Assistance

2024-11-15 · Thang M. Pham, Phat T. Nguyen, Seunghyun Yoon, Viet Dac Lai 외

While small language models (SLMs) show promises for mobile deployment, their real-world performance and applications on smartphones remains underexplored. We present SlimLM, a series of SLMs optimized for document assis…

Language ModelingLanguage ModellingQuestion AnsweringSmall Language Model

ReLF: Scalable Remote Live Forensics for Android

2021-10-20 · IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) 2021 10 · Ruipeng Zhang, Mengjun Xie, Jiang Bian

The world has witnessed the proliferation of mobile technologies as well as smartphone-related cybercrimes in recent years. However, due to high mobility of smartphones and tablets and transient nature of those attacks, …