# DeepEdgeBench: Benchmarking Deep Neural Networks on Edge Devices

arXiv: https://arxiv.org/abs/2108.09457 · HTML: https://mlsanity.com/paper/2108.09457/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 46 references that are in the map.
- First posted on arXiv 21 Aug 2021.

## Builds on (most cited first, 7 of 7)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [In-Datacenter Performance Analysis of a Tensor Processing Unit](https://mlsanity.com/paper/1704.04760/) (2017)
- [Benchmarking TinyML Systems: Challenges and Direction](https://mlsanity.com/paper/2003.04821/) (2020)
- [Benchmark Analysis of Representative Deep Neural Network Architectures](https://mlsanity.com/paper/1810.00736/) (2018)
- [Deep Learning in the Era of Edge Computing: Challenges and Opportunities](https://mlsanity.com/paper/2010.08861/) (2020)
- [Function Delivery Network: Extending Serverless Computing for Heterogeneous Platforms](https://mlsanity.com/paper/2102.02330/) (2021)

## Built on by (most cited first, 26 of 26)

- [A Survey on Deep Learning-Based Monocular Spacecraft Pose Estimation: Current State, Limitations and Prospects](https://mlsanity.com/paper/2305.07348/) (2023)
- [Training Machine Learning models at the Edge: A Survey](https://mlsanity.com/paper/2403.02619/) (2024)
- [Benchmarking Edge AI Platforms for High-Performance ML Inference](https://mlsanity.com/paper/2409.14803/) (2024)
- [A Comprehensive Evaluation of Deep Learning Object Detection Models on Heterogeneous Edge Devices](https://mlsanity.com/paper/2409.16808/) (2024)
- [A Performance Analysis of You Only Look Once Models for Deployment on Constrained Computational Edge Devices in Drone Applications](https://mlsanity.com/paper/2502.15737/) (2025)
- [Edge-Based Multimodal Sensor Data Fusion with Vision Language Models (VLMs) for Real-time Autonomous Vehicle Accident Avoidance](https://mlsanity.com/paper/2508.01057/) (2025)
- [Google Coral-based edge computing person reidentification using human parsing combined with analytical method](https://mlsanity.com/paper/2209.11024/) (2022)
- [Sustainable Edge Intelligence Through Energy-Aware Early Exiting](https://mlsanity.com/paper/2305.14094/) (2023)
- [Efficient Federated Fine-Tuning of Large Language Models with Layer Dropout](https://mlsanity.com/paper/2503.10217/) (2025)
- [Send Less, Save More: Energy-Efficiency Benchmark of Embedded CNN Inference vs. Data Transmission in IoT](https://mlsanity.com/paper/2510.24829/) (2025)
- [An Embedded Monocular Vision Approach for Ground-Aware Objects Detection and Position Estimation](https://mlsanity.com/paper/2207.09851/) (2022)
- [Benchmarking Jetson Edge Devices with an End-to-end Video-based Anomaly Detection System](https://mlsanity.com/paper/2307.16834/) (2023)
- [Energy efficiency in Edge TPU vs. embedded GPU for computer-aided medical imaging segmentation and classification](https://mlsanity.com/paper/2311.12876/) (2023)
- [Computer Vision Model Compression Techniques for Embedded Systems: A Survey](https://mlsanity.com/paper/2408.08250/) (2024)
- [A Study on Inference Latency for Vision Transformers on Mobile Devices](https://mlsanity.com/paper/2510.25166/) (2025)
- [Cloud to Edge: Benchmarking LLM Inference On Hardware-Accelerated Single-Board Computers](https://mlsanity.com/paper/2604.24785/) (2026)
- [Hydra: Phase-Aware Workload Characterization of LLM Inference across Edge SoC Generations, Backends, and Quantization Levels](https://mlsanity.com/paper/2608.25053/) (2026)
- [Edge Deep Learning Model Protection via Neuron Authorization](https://mlsanity.com/paper/2303.12397/) (2023)
- [Optimizing Deep Learning Models For Raspberry Pi](https://mlsanity.com/paper/2304.13039/) (2023)
- [Agile gesture recognition for capacitive sensing devices: adapting on-the-job](https://mlsanity.com/paper/2305.07624/) (2023)
- [E2GNN: Efficient Graph Neural Network Ensembles for Semi-Supervised Classification](https://mlsanity.com/paper/2405.03401/) (2024)
- [E2CAR: An Efficient 2D-CNN Framework for Real-Time EEG Artifact Removal on Edge Devices](https://mlsanity.com/paper/2602.09035/) (2026)
- [Pareto Optimal Benchmarking of AI Models on ARM Cortex Processors for Sustainable Embedded Systems](https://mlsanity.com/paper/2602.17508/) (2026)
- [Edge AI Deployment Beyond Models: A BSP-Aware Systems Framework for Industrial Embedded Platforms](https://mlsanity.com/paper/2605.26119/) (2026)
- [Lightweight Multi-Scale Anomaly Detection for Resource-Constrained Edge Devices](https://mlsanity.com/paper/2607.12599/) (2026)
- [Power-Performance Characterization of TinyML Systems](https://mlsanity.com/paper/2608.21646/) (2026)

## Abstract (arXiv)

EdgeAI (Edge computing based Artificial Intelligence) has been most actively researched for the last few years to handle variety of massively distributed AI applications to meet up the strict latency requirements. Meanwhile, many companies have released edge devices with smaller form factors (low power consumption and limited resources) like the popular Raspberry Pi and Nvidia's Jetson Nano for acting as compute nodes at the edge computing environments. Although the edge devices are limited in terms of computing power and hardware resources, they are powered by accelerators to enhance their performance behavior. Therefore, it is interesting to see how AI-based Deep Neural Networks perform on such devices with limited resources. In this work, we present and compare the performance in terms of inference time and power consumption of the four Systems on a Chip (SoCs): Asus Tinker Edge R, Raspberry Pi 4, Google Coral Dev Board, Nvidia Jetson Nano, and one microcontroller: Arduino Nano 33 BLE, on different deep learning models and frameworks. We also provide a method for measuring power consumption, inference time and accuracy for the devices, which can be easily extended to other devices. Our results showcase that, for Tensorflow based quantized model, the Google Coral Dev Board delivers the best performance, both for inference time and power consumption. For a low fraction of inference computation time, i.e. less than 29.3% of the time for MobileNetV2, the Jetson Nano performs faster than the other devices.