# FedDyMem: Efficient Federated Learning with Dynamic Memory and Memory-Reduce for Unsupervised Image Anomaly Detection

DevFeed: [FedDyMem: Efficient Federated Learning with Dynamic Memory and Memory-Reduce for Unsupervised Image Anomaly Detection](<https://devfeed.tech/articles/feddymem-efficient-federated-learning-with-dynamic-memory-and-memory-reduce-for-unsupervised-image-anomaly-detection-121250.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2502.21012>)

Author: Silin Chen, Andy Liu, Kangjian Di, Yichu Xu, Han-Jia Ye, Wenhan Luo, Ningmu Zou

Published: 2026-11-06T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Distributed Computing](<https://devfeed.tech/sources/arxiv-distributed-computing.md>)

Topics: [Federated Learning](<https://devfeed.tech/topics/federated-learning.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [image recognition](<https://devfeed.tech/topics/image-recognition.md>), [Image](<https://devfeed.tech/topics/image.md>)

Tags: [aggregation](<https://devfeed.tech/tags/aggregation.md>), [anomaly-detection](<https://devfeed.tech/tags/anomaly-detection.md>), [communication](<https://devfeed.tech/tags/communication.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-dc](<https://devfeed.tech/tags/cs-dc.md>), [data-privacy](<https://devfeed.tech/tags/data-privacy.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [decentralized](<https://devfeed.tech/tags/decentralized.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [feature](<https://devfeed.tech/tags/feature.md>), [federated-learning](<https://devfeed.tech/tags/federated-learning.md>), [generator](<https://devfeed.tech/tags/generator.md>), [global](<https://devfeed.tech/tags/global.md>), [image](<https://devfeed.tech/tags/image.md>), [industrial](<https://devfeed.tech/tags/industrial.md>), [localization](<https://devfeed.tech/tags/localization.md>), [manufacturing](<https://devfeed.tech/tags/manufacturing.md>), [medical](<https://devfeed.tech/tags/medical.md>), [memory](<https://devfeed.tech/tags/memory.md>), [metric](<https://devfeed.tech/tags/metric.md>), [model](<https://devfeed.tech/tags/model.md>), [overhead](<https://devfeed.tech/tags/overhead.md>)

## AI overview

FedDyMem shares reduced dynamic memory banks between clients and server instead of exchanging full model parameters for federated unsupervised image anomaly detection. Clients use a memory generator and metric loss to make normal-sample features more consistent and update their memory banks dynamically. Weighted-average memory reduction decreases bank size and communication overhead; the abstract reports that it also empirically lowers reconstruction fidelity under inversion attacks. The server aggregates global memory with k-means and distributes it to clients. Across six federated tasks built from eleven public industrial and medical datasets, the method reportedly improved anomaly detection and localization while reducing communication cost.

## Source excerpt

arXiv:2502.21012v3 Announce Type: replace Abstract: Unsupervised image anomaly detection (UAD) has become a critical process in industrial and medical applications, where models are trained on normal samples without requiring labeled anomalies. However, even normal images may contain sensitive product designs, manufacturing information, or institution-specific population characteristics, making centralized data collection difficult in practical deployments. Federated UAD provides a promising decentralized solution, but it remains challenging because clients use only normal training samples, their feature distributions remain highly heterogeneous within the same task, and communication should be efficient while limiting the exposure of sensitive client information. To address these challenges, we propose FedDyMem, an efficient federated learning method with dynamic memory and memory-reduce for unsupervised image anomaly detection. Instead of exchanging full model parameters, FedDyMem facilitates knowledge sharing between the clients and server through reduced dynamic memory banks. In the local clients, a memory generator and a metric loss are employed to improve the consistency of the feature distribution for normal samples, leveraging the local model to update the memory bank dynamically. For efficient communication and data privacy, a memory-reduce method based on weighted averages is proposed to significantly decrease the scale of memory banks. This representation reduces communication overhead and empirically lowers reconstruction fidelity under inversion attacks. On the server, global memory is constructed and distributed to individual clients through k-means aggregation. Experiments on six federated UAD tasks constructed from eleven public industrial and medical datasets show that FedDyMem consistently improves anomaly detection and localization while reducing communication cost.