Výsledky vyhledávání - "Couto, Rodrigo S."

Report

Improving Image-recognition Edge Caches with a Generative Adversarial Network

Autor: Souza, Guilherme B., Pacheco, Roberto G., Couto, Rodrigo S.

Image recognition is an essential task in several mobile applications. For instance, a smartphone can process a landmark photo to gather more information about its location. If the device does not have enough computational resources available, it off

Externí odkaz: http://arxiv.org/abs/2202.05929

Zobrazit plný text záznamu

Report

Early-exit deep neural networks for distorted images: providing an efficient edge offloading

Autor: Pacheco, Roberto G., Oliveira, Fernanda D. V. R., Couto, Rodrigo S.

Edge offloading for deep neural networks (DNNs) can be adaptive to the input's complexity by using early-exit DNNs. These DNNs have side branches throughout their architecture, allowing the inference to end earlier in the edge. The branches estimate

Externí odkaz: http://arxiv.org/abs/2108.09343

Zobrazit plný text záznamu

Report

Calibration-Aided Edge Inference Offloading via Adaptive Model Partitioning of Deep Neural Networks

Autor: Pacheco, Roberto G., Couto, Rodrigo S., Simeone, Osvaldo

Mobile devices can offload deep neural network (DNN)-based inference to the cloud, overcoming local hardware and energy limitations. However, offloading adds communication delay, thus increasing the overall inference time, and hence it should be used

Externí odkaz: http://arxiv.org/abs/2010.16335

Zobrazit plný text záznamu

Report

Inference Time Optimization Using BranchyNet Partitioning

Autor: Pacheco, Roberto G., Couto, Rodrigo S.

Deep Neural Network (DNN) applications with edge computing presents a trade-off between responsiveness and computational resources. On one hand, edge computing can provide high responsiveness deploying computational resources close to end devices, wh

Externí odkaz: http://arxiv.org/abs/2005.04099

Zobrazit plný text záznamu