Split Computing With Scalable Feature Compression for Visual Analytics on the Edge
Running deep visual analytics models for real-time applications is challenging for mobile
devices. Offloading the computation to edge server can mitigate computation bottleneck at …
devices. Offloading the computation to edge server can mitigate computation bottleneck at …
Scalable Feature Compression for Edge-Assisted Object Detection Over Time-Varying Networks
Z Yuan - In MLSys Workshop on Resource-Constrained …, 2023 - par.nsf.gov
Split-computing has recently emerged as a paradigm for offloading computation of visual
analytics models from low-powered mobile devices to edge or cloud servers, by which the …
analytics models from low-powered mobile devices to edge or cloud servers, by which the …
Feature compression for rate constrained object detection on the edge
Recent advances in computer vision has led to a growth of interest in deploying visual
analytics model on mobile devices. However, most mobile devices have limited computing …
analytics model on mobile devices. However, most mobile devices have limited computing …
Content-aware Input Scaling and Deep Learning Computation Offloading for Low-Latency Embedded Vision
Deploying deep learning (DL) models for visual recognition on embedded systems is often
constrained by their limited compute power and storage capacity and has stringent latency …
constrained by their limited compute power and storage capacity and has stringent latency …
Evaluation on the generalization of coded features across neural networks of different tasks
J Liu, A Liu, K Jia, H Yu, L Yu - 2023 IEEE International …, 2023 - ieeexplore.ieee.org
Recent advances in deep neural networks (DNNs) for computer vision tasks have made
intelligent analysis on edge devices more prevalent and practical. To better distribute …
intelligent analysis on edge devices more prevalent and practical. To better distribute …
Deepeye: Resource efficient local execution of multiple deep vision models using wearable commodity hardware
Wearable devices with built-in cameras present interesting opportunities for users to capture
various aspects of their daily life and are potentially also useful in supporting users with low …
various aspects of their daily life and are potentially also useful in supporting users with low …
Supervised compression for resource-constrained edge computing systems
There has been much interest in deploying deep learning algorithms on low-powered
devices, including smartphones, drones, and medical sensors. However, full-scale deep …
devices, including smartphones, drones, and medical sensors. However, full-scale deep …
Bottlefit: Learning compressed representations in deep neural networks for effective and efficient split computing
Although mission-critical applications require the use of deep neural networks (DNNs), their
continuous execution at mobile devices results in a significant increase in energy …
continuous execution at mobile devices results in a significant increase in energy …
FrankenSplit: Efficient Neural Feature Compression with Shallow Variational Bottleneck Injection for Mobile Edge Computing
The rise of mobile AI accelerators allows latency-sensitive applications to execute
lightweight Deep Neural Networks (DNNs) on the client side. However, critical applications …
lightweight Deep Neural Networks (DNNs) on the client side. However, critical applications …
Adaptive Compression Offloading and Resource Allocation for Edge Vision Computing
The rapid progress in edge computing (EC) and 5G wireless communication technology has
opened up novel opportunities for intelligent applications driven by Deep Neural Networks …
opened up novel opportunities for intelligent applications driven by Deep Neural Networks …