# Optimizing Edge Offloading Decisions for Object Detection

arXiv: https://arxiv.org/abs/2410.18919 · HTML: https://mlsanity.com/paper/2410.18919/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 48 references that are in the map.
- First posted on arXiv 24 Oct 2024.

## Builds on (most cited first, 27 of 27)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks](https://mlsanity.com/paper/1709.01686/) (2017)
- [R-FCN: Object Detection via Region-based Fully Convolutional Networks](https://mlsanity.com/paper/1605.06409/) (2016)
- [Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges](https://mlsanity.com/paper/2103.04505/) (2021)
- [TIDE: A General Toolbox for Identifying Object Detection Errors](https://mlsanity.com/paper/2008.08115/) (2020)
- [SPINN: Synergistic Progressive Inference of Neural Networks over Device and Cloud](https://mlsanity.com/paper/2008.06402/) (2020)
- [BottleNet++: An End-to-End Approach for Feature Compression in Device-Edge Co-Inference Systems](https://mlsanity.com/paper/1910.14315/) (2019)
- [JointDNN: An Efficient Training and Inference Engine for Intelligent Mobile Cloud Computing Services](https://mlsanity.com/paper/1801.08618/) (2018)
- [BottleNet: A Deep Learning Architecture for Intelligent Mobile Cloud Computing Services](https://mlsanity.com/paper/1902.01000/) (2019)
- [IDK Cascades: Fast Deep Learning by Learning not to Overthink](https://mlsanity.com/paper/1706.00885/) (2017)
- [Optimized Computation Offloading Performance in Virtual Edge Computing Systems via Deep Reinforcement Learning](https://mlsanity.com/paper/1805.06146/) (2018)
- [Adaptive Feeding: Achieving Fast and Accurate Detections by Adaptively Combining Object Detectors](https://mlsanity.com/paper/1707.06399/) (2017)
- [Edge-Cloud Collaborated Object Detection via Difficult-Case Discriminator](https://mlsanity.com/paper/2108.12858/) (2021)
- [Real-Time Edge Classification: Optimal Offloading under Token Bucket Constraints](https://mlsanity.com/paper/2010.13737/) (2020)
- [DeepScale: Online Frame Size Adaptation for Multi-object Tracking on Smart Cameras and Edge Servers](https://mlsanity.com/paper/2107.10404/) (2021)
- [CSL-YOLO: A New Lightweight Object Detection System for Edge Computing](https://mlsanity.com/paper/2107.04829/) (2021)
- [Progressive Neural Compression for Adaptive Image Offloading under Timing Constraints](https://mlsanity.com/paper/2310.05306/) (2023)
- [Adaptive Edge Offloading for Image Classification Under Rate Limit](https://mlsanity.com/paper/2208.00485/) (2022)

## Built on by (most cited first, 2 of 2)

- [Budget-Adaptive Routing: Skipping the Weak When the Strong Answers Anyway](https://mlsanity.com/paper/2606.30919/) (2026)
- [The Decision Value of Perception Compute](https://mlsanity.com/paper/2609.35910/) (2026)

## Abstract (arXiv)

Recent advances in machine learning and hardware have produced embedded devices capable of performing real-time object detection with commendable accuracy. We consider a scenario in which embedded devices rely on an onboard object detector, but have the option to offload detection to a more powerful edge server when local accuracy is deemed too low. Resource constraints, however, limit the number of images that can be offloaded to the edge. Our goal is to identify which images to offload to maximize overall detection accuracy under those constraints. To that end, the paper introduces a reward metric designed to quantify potential accuracy improvements from offloading individual images, and proposes an efficient approach to make offloading decisions by estimating this reward based only on local detection results. The approach is computationally frugal enough to run on embedded devices, and empirical findings indicate that it outperforms existing alternatives in improving detection accuracy even when the fraction of offloaded images is small.