Towards Scalable IoT Deployment for Visual Anomaly Detection via Efficient Compression

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Stropeni, Arianna, Borsatti, Francesco, Barusco, Manuel, Pezze, Davide Dalle, Fabris, Marco, Susto, Gian Antonio
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911315887390720
author Stropeni, Arianna
Borsatti, Francesco
Barusco, Manuel
Pezze, Davide Dalle
Fabris, Marco
Susto, Gian Antonio
author_facet Stropeni, Arianna
Borsatti, Francesco
Barusco, Manuel
Pezze, Davide Dalle
Fabris, Marco
Susto, Gian Antonio
contents Visual Anomaly Detection (VAD) is a key task in industrial settings, where minimizing operational costs is essential. Deploying deep learning models within Internet of Things (IoT) environments introduces specific challenges due to limited computational power and bandwidth of edge devices. This study investigates how to perform VAD effectively under such constraints by leveraging compact, efficient processing strategies. We evaluate several data compression techniques, examining the tradeoff between system latency and detection accuracy. Experiments on the MVTec AD benchmark demonstrate that significant compression can be achieved with minimal loss in anomaly detection performance compared to uncompressed data. Current results show up to 80% reduction in end-to-end inference time, including edge processing, transmission, and server computation.
format Preprint
id arxiv_https___arxiv_org_abs_2505_07119
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Scalable IoT Deployment for Visual Anomaly Detection via Efficient Compression
Stropeni, Arianna
Borsatti, Francesco
Barusco, Manuel
Pezze, Davide Dalle
Fabris, Marco
Susto, Gian Antonio
Computer Vision and Pattern Recognition
Artificial Intelligence
Visual Anomaly Detection (VAD) is a key task in industrial settings, where minimizing operational costs is essential. Deploying deep learning models within Internet of Things (IoT) environments introduces specific challenges due to limited computational power and bandwidth of edge devices. This study investigates how to perform VAD effectively under such constraints by leveraging compact, efficient processing strategies. We evaluate several data compression techniques, examining the tradeoff between system latency and detection accuracy. Experiments on the MVTec AD benchmark demonstrate that significant compression can be achieved with minimal loss in anomaly detection performance compared to uncompressed data. Current results show up to 80% reduction in end-to-end inference time, including edge processing, transmission, and server computation.
title Towards Scalable IoT Deployment for Visual Anomaly Detection via Efficient Compression
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2505.07119