Parameter Efficient Multi-Class Intelligent Scheduling for Multimodal Online Distributed Industrial Anomaly Detection

Heqiang Wang, Weihong Yang, Zheyuan Yang, Jia Zhou, Xiaoxiong Zhong, Fangming Liu, Weizhe Zhang

arXiv:2605.23984 · 2026-05-26 공개 · arXiv · PDF

parameter-efficient low-rank-adaptation distributed-training online-learning edge-intelligence resource-constrained modiad industrial-sensors

Abstract

Industrial anomaly detection has attracted significant attention as a fundamental challenge in industrial systems. The rapid advancement of heterogeneous industrial sensors has driven industrial anomaly detection from unimodal to multimodal paradigms. However, existing methods are primarily designed for centralized and offline settings, overlooking the distributed and continuously generated data characteristic of real-world industrial environments. With the advancement of edge intelligence, modern edge devices are increasingly capable of not only data acquisition but also distributed model training, enabling collaborative intelligence across the system. Industrial anomaly detection represents a critical application in this context. Motivated by these challenges, we propose a novel framework termed Multimodal Online Distributed Industrial Anomaly Detection (MODIAD). We first present a comprehensive workflow for MODIAD and then formulate a Multi-class Intelligent Scheduling (MIS) problem to coordinate cross class model updates by balancing data sufficiency and class update frequency. To efficiently solve this problem, we design a Sequential Marginal Gain Greedy (SMG) algorithm that enables effective multi-class training under resource constraints. Furthermore, to improve the computational and communication efficiency during training, we propose an Resource Efficient Class-Wise Low Rank Adaptation (REC-LoRA) strategy, which significantly reduces system overhead while preserving detection performance. Extensive experiments on two representative multimodal industrial anomaly detection datasets, MVTec 3D-AD and Eyecandies demonstrate that the proposed approach achieves superior performance and efficiency under the MODIAD scenario.

한국어 요약

📋 한 줄 요약

**[산업 이상 탐지 / Multimodal Edge]** MODIAD가 multimodal·online·distributed 산업 이상 탐지를 통합 — Multi-class Intelligent Scheduling을 SMG greedy로 풀고 REC-LoRA로 통신·연산 효율 강화, MVTec 3D-AD·Eyecandies 우수 성능.

🎯 핵심 기여도

💡 핵심 아이디어

실세계 산업 이상 탐지는 multimodal·distributed·online 환경에서 동작해야 하며, multi-class 업데이트 스케줄링을 marginal-gain greedy로 풀고 class-wise low-rank adaptation으로 자원 효율을 보존하면 detection 성능을 유지하면서 분산 학습 효율을 확보할 수 있다.

🔬 기술적 접근법

📊 주요 결과

💭 의의 및 한계

**의의**: 산업 이상 탐지의 multimodal·distributed·online 환경 통합 첫 체계 프레임워크, edge intelligence 추세에 부합, scheduling·LoRA 결합으로 실용 자원 효율 확보. **한계**: 2 데이터셋 평가의 일반화, multimodal sensor 종류 확장 시 architecture 적응, 매우 큰 edge device 수에서의 scaling은 후속.

🚀 실용적 활용