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

by   Roberto G. Pacheco, et al.

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 the accuracy for a given input. If this estimated accuracy reaches a threshold, the inference ends on the edge. Otherwise, the edge offloads the inference to the cloud to process the remaining DNN layers. However, DNNs for image classification deals with distorted images, which negatively impact the branches' estimated accuracy. Consequently, the edge offloads more inferences to the cloud. This work introduces expert side branches trained on a particular distortion type to improve robustness against image distortion. The edge detects the distortion type and selects appropriate expert branches to perform the inference. This approach increases the estimated accuracy on the edge, improving the offloading decisions. We validate our proposal in a realistic scenario, in which the edge offloads DNN inference to Amazon EC2 instances.


page 1

page 2

page 3

page 4


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

Mobile devices can offload deep neural network (DNN)-based inference to ...

Edge-Cloud Cooperation for DNN Inference via Reinforcement Learning and Supervised Learning

Deep Neural Networks (DNNs) have been widely applied in Internet of Thin...

Cost-Driven Offloading for DNN-based Applications over Cloud, Edge and End Devices

Currently, deep neural networks (DNNs) have achieved a great success in ...

SplitEE: Early Exit in Deep Neural Networks with Split Computing

Deep Neural Networks (DNNs) have drawn attention because of their outsta...

Optimizing Deep Learning Inference on Embedded Systems Through Adaptive Model Selection

Deep neural networks ( DNNs ) are becoming a key enabling technology for...

Scission: Context-aware and Performance-driven Edge-based Distributed Deep Neural Networks

Partitioning and distributing deep neural networks (DNNs) across end-dev...

Offloading Algorithms for Maximizing Inference Accuracy on Edge Device Under a Time Constraint

With the emergence of edge computing, the problem of offloading jobs bet...

Please sign up or login with your details

Forgot password? Click here to reset