mlsanityData to 7 Oct 2026

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

arXiv 2108.09343 ↗First posted 20 Aug 2021cs.CV cs.LG cs.NIcited by 8

On the map: Efficient LLM inference and serving → Early exit and edge inference

Abstract (arXiv)

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.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Placed in Early exit and edge inference, one of 12 directions in Efficient LLM inference and serving. Builds on 11 of its 20 references that are in the map. First posted on arXiv 20 Aug 2021.

Builds on

11 of 20 references.

References · 11

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  3. 2017BranchyNet: Fast Inference via Early Exiting from Deep Neural Networkscited by 591
  4. 2017Distributed Deep Neural Networks over the Cloud, the Edge and End Devicescited by 119
  5. 2016Understanding How Image Quality Affects Deep Neural Networkscited by 118
  6. 2020SPINN: Synergistic Progressive Inference of Neural Networks over Device and Cloudcited by 109
  7. 2017On Classification of Distorted Images with Deep Convolutional Neural Networkscited by 26
  8. 2017DeepCorrect: Correcting DNN models against Image Distortionscited by 14
  9. 2016Towards Robust Deep Neural Networks with BANGcited by 8
  10. 2020Calibration-Aided Edge Inference Offloading via Adaptive Model Partitioning of Deep Neural Networkscited by 8
  11. 2020Inference Time Optimization Using BranchyNet Partitioningcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 1; 2023: 1; 2024: 3; 2025: 1; 2026: 1.

8 papers.

  1. 2021Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AIcited by 38
  2. 2023SplitEE: Early Exit in Deep Neural Networks with Split Computingcited by 13
  3. 2022Unsupervised Early Exit in DNNs with Multiple Exitscited by 10
  4. 2024I-SplitEE: Image classification in Split Computing DNNs with Early Exitscited by 9
  5. 2024Distributed Inference on Mobile Edge and Cloud: An Early Exit based Clustering Approachcited by 3
  6. 2024Distributed Inference on Mobile Edge and Cloud: A Data-Cartography based Clustering Approachcited by 0
  7. 2025Know What You Don't Know: Selective Prediction for Early Exit DNNscited by 0
  8. 2026A Comparative Analysis on the Performance of Upper Confidence Bound Algorithms in Adaptive Deep Neural Networkscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Adaptive Deep Neural Network Inference Optimization with EENet
  2. 2024Early-exit Convolutional Neural Networks
  3. 2026A Comparative Study of CNN Optimization Methods for Edge AI: Exploring the Role of Early Exits
  4. 2024A Converting Autoencoder Toward Low-latency and Energy-efficient DNN Inference at the Edge
  5. 2023Early-Exit with Class Exclusion for Efficient Inference of Neural Networks
  6. 2022Resource-Constrained Edge AI with Early Exit Prediction
  7. 2025ERDE: Entropy-Regularized Distillation for Early-exit
  8. 2021Adaptive Inference through Early-Exit Networks: Design, Challenges and Directions