# Towards Scalable IoT Deployment for Visual Anomaly Detection via Efficient Compression

arXiv: https://arxiv.org/abs/2505.07119 · HTML: https://mlsanity.com/paper/2505.07119/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 29 references that are in the map.
- First posted on arXiv 11 May 2025.

## Builds on (most cited first, 16 of 16)

- [Towards Total Recall in Industrial Anomaly Detection](https://mlsanity.com/paper/2106.08265/) (2021)
- [PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization](https://mlsanity.com/paper/2011.08785/) (2020)
- [CutPaste: Self-Supervised Learning for Anomaly Detection and Localization](https://mlsanity.com/paper/2104.04015/) (2021)
- [DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detection](https://mlsanity.com/paper/2108.07610/) (2021)
- [SimpleNet: A Simple Network for Image Anomaly Detection and Localization](https://mlsanity.com/paper/2303.15140/) (2023)
- [FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows](https://mlsanity.com/paper/2111.07677/) (2021)
- [CFA: Coupled-hypersphere-based Feature Adaptation for Target-Oriented Anomaly Localization](https://mlsanity.com/paper/2206.04325/) (2022)
- [Deep feature compression for collaborative object detection](https://mlsanity.com/paper/1802.03931/) (2018)
- [PaSTe: Improving the Efficiency of Visual Anomaly Detection at the Edge](https://mlsanity.com/paper/2410.11591/) (2024)
- [IoT Anomaly Detection Methods and Applications: A Survey](https://mlsanity.com/paper/2207.09092/) (2022)
- [Efficient Sensors Selection for Traffic Flow Monitoring: An Overview of Model-Based Techniques leveraging Network Observability](https://mlsanity.com/paper/2404.08588/) (2024)
- [Visual Sensor Network Stimulation Model Identification via Gaussian Mixture Model and Deep Embedded Features](https://mlsanity.com/paper/2201.06804/) (2022)
- [Omni-AD: Learning to Reconstruct Global and Local Features for Multi-class Anomaly Detection](https://mlsanity.com/paper/2503.21125/) (2025)
- [Secure Consensus via Objective Coding: Robustness Analysis to Channel Tampering](https://mlsanity.com/paper/2107.04276/) (2021)
- [On the impact of regularization in data-driven predictive control](https://mlsanity.com/paper/2304.00263/) (2023)
- [A Robustness Analysis to Structured Channel Tampering Over Secure-by-Design Consensus Networks](https://mlsanity.com/paper/2306.13427/) (2023)

## Built on by (most cited first, 1 of 1)

- [MoViAD: A Modular Library for Visual Anomaly Detection](https://mlsanity.com/paper/2507.12049/) (2025)

## Abstract (arXiv)

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.