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

• URL: http://arxiv.org/abs/2108.09343v1
• Date: Fri, 20 Aug 2021 19:52:55 GMT
• Title: Early-exit deep neural networks for distorted images: providing an efficient edge offloading
• Authors: Roberto G. Pacheco, Fernanda D.V.R. Oliveira and Rodrigo S. Couto
• Abstract summary: Edge offloading for deep neural networks (DNNs) can be adaptive to the input's complexity. We introduce expert side branches trained on a particular distortion type to improve against image distortion. This approach increases the estimated accuracy on the edge, improving the offloading decisions.
• Score: 69.43216268165402
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• A Converting Autoencoder Toward Low-latency and Energy-efficient DNN Inference at the Edge [4.11949030493552]
  We present CBNet, a low-latency and energy-efficient deep neural network (DNN) inference framework tailored for edge devices. It utilizes a "converting" autoencoder to efficiently transform hard images into easy ones. CBNet achieves up to 4.8x speedup in inference latency and 79% reduction in energy usage compared to competing techniques.
  arXiv  Detail & Related papers  (2024-03-11T08:13:42Z)
• Revisiting Edge Perturbation for Graph Neural Network in Graph Data Augmentation and Attack [58.440711902319855]
  Edge perturbation is a method to modify graph structures. It can be categorized into two veins based on their effects on the performance of graph neural networks (GNNs) We propose a unified formulation and establish a clear boundary between two categories of edge perturbation methods.
  arXiv  Detail & Related papers  (2024-03-10T15:50:04Z)
• I-SplitEE: Image classification in Split Computing DNNs with Early Exits [5.402030962296633]
  Large size of Deep Neural Networks (DNNs) hinders deploying them on resource-constrained devices like edge, mobile, and IoT platforms. Our work presents an innovative unified approach merging early exits and split computing. I-SplitEE is an online unsupervised algorithm ideal for scenarios lacking ground truths and with sequential data.
  arXiv  Detail & Related papers  (2024-01-19T07:44:32Z)
• Efficient Link Prediction via GNN Layers Induced by Negative Sampling [92.05291395292537]
  Graph neural networks (GNNs) for link prediction can loosely be divided into two broad categories. First, emphnode-wise architectures pre-compute individual embeddings for each node that are later combined by a simple decoder to make predictions. Second, emphedge-wise methods rely on the formation of edge-specific subgraph embeddings to enrich the representation of pair-wise relationships.
  arXiv  Detail & Related papers  (2023-10-14T07:02:54Z)
• Bring Your Own View: Graph Neural Networks for Link Prediction with Personalized Subgraph Selection [57.34881616131377]
  We introduce a Personalized Subgraph Selector (PS2) as a plug-and-play framework to automatically, personally, and inductively identify optimal subgraphs for different edges. PS2 is instantiated as a bi-level optimization problem that can be efficiently solved differently. We suggest a brand-new angle towards GNNLP training: by first identifying the optimal subgraphs for edges; and then focusing on training the inference model by using the sampled subgraphs.
  arXiv  Detail & Related papers  (2022-12-23T17:30:19Z)
• Unsupervised Early Exit in DNNs with Multiple Exits [0.0]
  We focus on Elastic BERT, a pre-trained multi-exit DNN to demonstrate that it nearly' satisfies the Strong Dominance (SD) property. We empirically validate our algorithm on IMDb and Yelp datasets.
  arXiv  Detail & Related papers  (2022-09-20T05:35:54Z)
• Calibration-Aided Edge Inference Offloading via Adaptive Model Partitioning of Deep Neural Networks [30.800324092046793]
  Mobile devices can offload deep neural network (DNN)-based inference to the cloud, overcoming local hardware and energy limitations. This work shows that the employment of a miscalibrated early-exit DNN for offloading via model partitioning can significantly decrease inference accuracy. In contrast, we argue that implementing a calibration algorithm prior to deployment can solve this problem, allowing for more reliable offloading decisions.
  arXiv  Detail & Related papers  (2020-10-30T15:50:12Z)
• Shape Defense Against Adversarial Attacks [47.64219291655723]
  Humans rely heavily on shape information to recognize objects. Conversely, convolutional neural networks (CNNs) are biased more towards texture. Here, we explore how shape bias can be incorporated into CNNs to improve their robustness. Two algorithms are proposed, based on the observation that edges are invariant to moderate imperceptible perturbations.
  arXiv  Detail & Related papers  (2020-08-31T03:23:59Z)
• Hold me tight! Influence of discriminative features on deep network boundaries [63.627760598441796]
  We propose a new perspective that relates dataset features to the distance of samples to the decision boundary. This enables us to carefully tweak the position of the training samples and measure the induced changes on the boundaries of CNNs trained on large-scale vision datasets.
  arXiv  Detail & Related papers  (2020-02-15T09:29:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.