DeepX: A Software Accelerator for Low-Power Deep Learning Inference on Mobile Devices

By Nicholas Donald Lane, Sourav Bhattacharya, Petko Georgiev, Claudio Forlivesi, Lei Jiao, Lorena Qendro, F. Kawsar. 2016

568 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Computer Vision and Pattern Recognition

Citations in the corpus

Deep Learning for IoT Big Data and Streaming Analytics: A Survey (2017, methodology): “Accelerators [91] [185] [190] [191] [192] [193] • Integrates DL model with the hardware • Efficient computations • Does not work with the traditional hardware platforms”
AutoFL: Enabling Heterogeneity-Aware Energy Efficient Federated Learning (2021, methodology): “While on-device inference is becoming more ubiquitous [14,29,41,57,62,65,101,102,119,125,137], performing ML model training in the cloud is still the standard practice for most use cases [1, 29, 43, 54, 81, 88, 101], due to the significant computation and memory resource requirements [9, 35, 69, 100”
RILOD: near real-time incremental learning for object detection at the edge (2019, background): “he recent development of light-weight deep learning SDKs [1, 21, 30, 35]. Researchers have focused on reducing the computation cost on the edge devices by compressing pre-trained deep learning models [3, 9, 10, 20], designing lightweight neural network architectures [13, 16], or hardware acceleratio”
Dynamic Adaptive DNN Surgery for Inference Acceleration on the Edge (2019, background): “DeepX [23] explored the opportunities to use mobile GPUs to enable real-time deep learning inferences.”
NestDNN: Resource-Aware Multi-Tenant On-Device Deep Learning for Continuous Mobile Vision (2018, methodology): “…this technique has gained considerable popularity and has been applied to developing state-of-the-art mobile deep learning systems [8, 14, 17, 20, 38], it has a key drawback : since application developers develop their applications independently, the resource-accuracy trade-off of the…”
Survey on Deep Neural Networks in Speech and Vision Systems (2019, background): “Deep X software accelerator, 2016 [186] 866.”
DeepSense: A Unified Deep Learning Framework for Time-Series Mobile Sensing Data Processing (2016, methodology): “DeepX [21], RedEye [26], and ConvTransfer [30] reduce the energy consumption or training time of deep neural networks, based on software and hardware, respectively.”
Efficient Incremental Learning for Mobile Object Detection (2019, background): “Researchers have focused on reducing the computation cost on the mobile devices by compressing pre-trained deep learning models [10, 9, 20, 3], designing lightweight neural network architectures [16, 13], or hardware accelerations [15, 37] — these papers have not addressed the incremental learning…”
AutoScale: Optimizing Energy Efficiency of End-to-End Edge Inference under Stochastic Variance (2020, methodology): “Other works explored the use of reinforcement learning to handle runtime variance for web browsers, for latency-critical cloud services, and for CPUs [12, 64, 71].”
SPINN: synergistic progressive inference of neural networks over device and cloud (2020, methodology): “have been proposed, from compiler [1, 30, 65] and runtime optimisations [36, 43, 49] to custom cloud [7, 19, 34] and accelerator”
Cloud-Based or On-Device: An Empirical Study of Mobile Deep Inference (2017, background): “However, recent development of mobile specific deep learning optimizations [37], [38], [3], [17], [15], [16] and improvement in mobile GPU energy consumption [28] are promising improvements towards efficient mobile-based deep learning apps.”
Deep k-Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutions (2018, methodology): “Various CNN compression techniques have been proposed, such as weight compression (Bhattacharya & Lane, 2016) (Han et al., 2016) (Lane et al., 2016) and decomposition (Changpinyo et al., 2017) (Howard et al., 2017) (Wang et al., 2015), and compact architectures (Iandola et al., 2016) (Lin et al.,…”
Federated Learning for Internet of Things: A Comprehensive Survey (2021, methodology): “The work in [205] introduces a software-based deep learning accelerator to support AI/DL training on mobile hardware.”
C-GOOD: C-code Generation Framework for Optimized On-device Deep Learning (2018, methodology): “DeepX[21] is a software accelerator for deep learning to com-”
Machine Learning at the Network Edge: A Survey (2019, methodology): “ullModel objectrecognition[77] SparseSep - Linux Android FullModel mobileobjectrecognition audioclassiﬁcation[15] DeepX C++,Java, Lua Linux Android FullModel mobileobjectrecognition audioclassiﬁcation[75] Edgent - Ubuntu Majorpart oftheDNN imagerecognition[78] daBNN ArmAssembly, C++,Java MobileOSs (”
Occlumency: Privacy-preserving Remote Deep-learning Inference Using SGX (2019, methodology): “Another approach is on-device DL inference [43, 51, 80], which aims to run DL inference locally on off-the-shelf mobile/IoT devices by compressing models or designing new lightweight models.”
EnergyNet: Energy-Efficient Dynamic Inference (2018, background): “Most of them aim to reduce the model size or the number of 28 computations [3, 4, 5, 6, 7, 8, 9, 10, 11, 12].”
On-Demand Deep Model Compression for Mobile Devices: A Usage-Driven Model Selection Framework (2018, methodology): “The scheduler proposed in [13] and [25] can be combined when extending AdaDeep to mobile platforms with heterogenous resources.”