Accelerating Data Preprocessing for Efficient Vision Model Inference on Jetson Edge Device

[2608.27655] Accelerating Data Preprocessing for Efficient Vision Model Inference on Jetson Edge Device Skip to main content Search Submit Donate Log in Computer Science > Performance arXiv:2608.27655 (cs) [Submitted on 27 Aug 2026] Title: Accelerating Data Preprocessing for Efficient Vision Model Inference on Jetson Edge Device Authors: Tian Chen , Nawras Alnaasan , Jinghan Yao , Aamir Shafi , Hari Subramoni , Dhabaleswar K. (DK) Panda View PDF HTML (experimental) Abstract: Data preprocessing is a crucial part of deep learning workflows on edge devices. However, decoding data saved in JPEG format is very compute-intensive and occupies a major portion of the preprocessing pipeline. Therefore, increasing the decoding speed is vital for improving overall throughput, especially for inputs with large image sizes, which are often subject to preprocessing bottlenecks. On the other hand, edge devices are equipped with specialized hardware units to accelerate media processing and image decoding. For instance, the NVIDIA Jetson platform possesses a dedicated NVJPEG unit. These units can be used to enhance the performance of the preprocessing pipeline. This paper introduces the utilization of such specific hardware acceleration units for offloading decoding tasks. By combining this with a multi-instance approach, it allows for the parallelization of all compute resources including CPU, NVJPEG, GPU, and DLA in Jetson devices. In this work, we compare various potential pipeline designs. On ResNet18, ResNet50, and ResNet152, three models with different sizes, we evaluate the impact of batch sizes and image sizes, as well as the characteristics of GPU/DLA inference. Finally, a fine-tuning experiment for multi-instance design has been conducted. The multi-instance design with a specific hardware decoding unit involved offers up to 30.02% speedup for large image sizes, compared with the most optimized design without it. Based on these findings, we demonstrate the benefits of using the NVJPEG unit in deep learning workflows and provide guidelines for tuning and optimizing edge inference workflows. Subjects: Performance (cs.PF) Cite as: arXiv:2608.27655 [cs.PF] (or arXiv:2608.27655v1 [cs.PF] for this version) https://doi.org/10.48550/arXiv.2608.27655 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Tian Chen [ view email ] [v1] Thu, 27 Aug 2026 19:42:56 UTC (2,527 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.PF < prev | next > new | recent | 2026-08 Change to browse by: cs References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• Accelerating Data Preprocessing for Efficient Vision Model Inference on Jetson Edge Device#780955
• Official Review · ICLR 2025#787197
• FlashBoB: I/O-Efficient Exact Backward-over-Backward for Softmax Attention#1050275
• Adaptive Spectral Feature Forecasting for Diffusion Sampling Acceleration#1142633
• DeepSeek-V4-Flash on AMD gfx90a: Correctness Recovery and Inference Performance Engineering#1160736