Split computing and early exiting for deep learning applications: Survey and research challenges
Mobile devices such as smartphones and autonomous vehicles increasingly rely on deep
neural networks (DNNs) to execute complex inference tasks such as image classification …
neural networks (DNNs) to execute complex inference tasks such as image classification …
SyRoC: Symbiotic robotics for QoS-aware heterogeneous applications in IoT-edge-cloud computing paradigm
Smart Robots, as an advanced domain of widespread concern, can be applied in diverse
fields to perform compute-intensive Internet of Things (IoT) applications. However, their …
fields to perform compute-intensive Internet of Things (IoT) applications. However, their …
Re-thinking computation offload for efficient inference on IoT devices with duty-cycled radios
While a number of recent efforts have explored the use of" cloud offload" to enable deep
learning on IoT devices, these have not assumed the use of duty-cycled radios like BLE. We …
learning on IoT devices, these have not assumed the use of duty-cycled radios like BLE. We …
A hybrid fast inference approach with distributed neural networks for edge computing enabled UAV swarm
P Zhang, H Tian, H Luo, XW Li, GF Nie - Physical Communication, 2023 - Elsevier
Nowadays, unmanned aerial vehicle (UAV) swarm supported by mobile edge computing is
attracting more and more attention, such as smart agriculture, smart transportation, smart …
attracting more and more attention, such as smart agriculture, smart transportation, smart …
Communication-oriented model fine-tuning for packet-loss resilient distributed inference under highly lossy IoT networks
The distributed inference (DI) framework has gained traction as a technique for real-time
applications empowered by cutting-edge deep machine learning (ML) on resource …
applications empowered by cutting-edge deep machine learning (ML) on resource …
[HTML][HTML] Model and system robustness in distributed CNN inference at the edge
Prevalent large CNN models pose a significant challenge in terms of computing resources
for resource-constrained devices at the Edge. Distributing the computations and coefficients …
for resource-constrained devices at the Edge. Distributing the computations and coefficients …
Privacy Set: Privacy Authority-Aware Compiler for Homomorphic Encryption on Edge-Cloud System
Fully homomorphic encryption (FHE) offers a promising solution for privacy-preserving cloud
computing by allowing cloud servers to compute on encrypted data without decryption …
computing by allowing cloud servers to compute on encrypted data without decryption …
NAIR: An Efficient Distributed Deep Learning Architecture for Resource Constrained IoT System
Y Xiao, D Zhang, Y Wang, X Dai… - IEEE Internet of …, 2024 - ieeexplore.ieee.org
The distributed deep learning architecture can support the front-deployment of deep
learning systems in resource constrained Internet of Things devices and is attracting …
learning systems in resource constrained Internet of Things devices and is attracting …
Logan: Loss-tolerant Live Video Analytics System
Cloud-based live video analytics with tight latency bound is gaining importance to support
emerging applications such as UAVs and augmented reality. However, existing systems …
emerging applications such as UAVs and augmented reality. However, existing systems …
CACTUS: Dynamically Switchable Context-aware micro-Classifiers for Efficient IoT Inference
While existing strategies to execute deep learning-based classification on low-power
platforms assume the models are trained on all classes of interest, this paper posits that …
platforms assume the models are trained on all classes of interest, this paper posits that …