# Benchmarking Deep Learning Models on NVIDIA Jetson Nano for Real-Time Systems: An Empirical Investigation

arXiv: https://arxiv.org/abs/2406.17749 · HTML: https://mlsanity.com/paper/2406.17749/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 24 references that are in the map.
- First posted on arXiv 25 Jun 2024.

## Builds on (most cited first, 6 of 6)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Medical Image Segmentation Review: The success of U-Net](https://mlsanity.com/paper/2211.14830/) (2022)
- [Chasing Carbon: The Elusive Environmental Footprint of Computing](https://mlsanity.com/paper/2011.02839/) (2020)
- [PriorBand: Practical Hyperparameter Optimization in the Age of Deep Learning](https://mlsanity.com/paper/2306.12370/) (2023)

## Built on by (most cited first, 9 of 9)

- [Enhancing Autonomous Driving Systems with On-Board Deployed Large Language Models](https://mlsanity.com/paper/2504.11514/) (2025)
- [Embodied Foundation Models at the Edge: A Survey of Deployment Constraints and Mitigation Strategies](https://mlsanity.com/paper/2603.16952/) (2026)
- [LLMs are everywhere: Ubiquitous Utilization of AI Models through Air Computing](https://mlsanity.com/paper/2503.00767/) (2025)
- [Learning Before Filtering: Real-Time Hardware Learning at the Detector Level](https://mlsanity.com/paper/2506.11981/) (2025)
- [FEDEXCHANGE: Bridging the Domain Gap in Federated Object Detection for Free](https://mlsanity.com/paper/2509.10503/) (2025)
- [Dual-stage and Lightweight Patient Chart Summarization for Emergency Physicians](https://mlsanity.com/paper/2510.06263/) (2025)
- [K-Track: Kalman-Enhanced Tracking for Accelerating Deep Point Trackers on Edge Devices](https://mlsanity.com/paper/2512.10628/) (2025)
- [EdgeVTP: Exploration of Latency-efficient Trajectory Prediction for Edge-based Embedded Vision Applications](https://mlsanity.com/paper/2604.16783/) (2026)
- [TS-MAMP: A Remanufactured Agricultural Robot with Second-Life EV Components and NMS-Free On-Device Weed Detection](https://mlsanity.com/paper/2608.02270/) (2026)

## Abstract (arXiv)

The proliferation of complex deep learning (DL) models has revolutionized various applications, including computer vision-based solutions, prompting their integration into real-time systems. However, the resource-intensive nature of these models poses challenges for deployment on low-computational power and low-memory devices, like embedded and edge devices. This work empirically investigates the optimization of such complex DL models to analyze their functionality on an embedded device, particularly on the NVIDIA Jetson Nano. It evaluates the effectiveness of the optimized models in terms of their inference speed for image classification and video action detection. The experimental results reveal that, on average, optimized models exhibit a 16.11% speed improvement over their non-optimized counterparts. This not only emphasizes the critical need to consider hardware constraints and environmental sustainability in model development and deployment but also underscores the pivotal role of model optimization in enabling the widespread deployment of AI-assisted technologies on resource-constrained computational systems. It also serves as proof that prioritizing hardware-specific model optimization leads to efficient and scalable solutions that substantially decrease energy consumption and carbon footprint.