arXiv 2604.109712026-04-13cs.CVcs.AI

MMR-AD：一个大规模多模态数据集，用于基于多模态大语言模型的通用异常检测基准测试

MMR-AD: A Large-Scale Multimodal Dataset for Benchmarking General Anomaly Detection with Multimodal Large Language Models

School of Information Science and Electronic Engineering, Shanghai Jiao Tong University（上海交通大学电子信息与电气工程学院）；MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University（上海交通大学人工智能研究院教育部人工智能重点实验室）

Xincheng Yao, Zefeng Qian, Chao Shi, Jiayang Song, Chongyang Zhang

备注：: Accepted by CVPR2026

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出MMR-AD数据集，用于评估多模态大语言模型在通用异常检测中的性能，揭示当前SOTA模型与工业需求的差距，并提出基于推理的Anomaly-R1模型，实现了异常检测与定位的显著提升。

摘要：

在工业异常检测的发展过程中，通用异常检测（GAD）已成为一种新兴趋势和最终目标。不同于传统的单类和多类异常检测，通用异常检测旨在训练一个能够直接检测多样新类中异常的通用异常检测模型，而无需对目标数据进行重新训练或微调。最近，多模态大语言模型（MLLMs）因其革命性的视觉理解和语言推理能力，在实现通用异常检测方面展现出巨大潜力。然而，由于（1）MLLMs在预训练时使用了大量来自网络的数据，这些数据与AD场景中的数据仍有显著差距，且预训练期间的图像-文本对并非专门针对AD任务；（2）目前主流的异常检测数据集基于图像，尚未适用于训练后MLLMs的评估。为了促进基于MLLM的通用异常检测研究，我们提出了MMR-AD，这是一个全面的基准，用于训练和评估基于MLLM的异常检测模型。通过MMR-AD，我们发现当前最先进的通用MLLMs在异常检测性能上仍远低于工业需求。基于MMR-AD，我们还提出了一种基线模型Anomaly-R1，这是一种基于推理的异常检测模型，该模型从MMR-AD中的CoT数据中学习，并通过强化学习进一步增强。大量实验表明，我们的Anomaly-R1在异常检测和定位方面均显著优于通用MLLMs。

英文摘要：

In the progress of industrial anomaly detection, general anomaly detection (GAD) is an emerging trend and also the ultimate goal. Unlike the conventional single- and multi-class AD, general AD aims to train a general AD model that can directly detect anomalies in diverse novel classes without any retraining or fine-tuning on the target data. Recently, Multimodal Large Language Models (MLLMs) have shown great promise in achieving general anomaly detection due to their revolutionary visual understanding and language reasoning capabilities. However, MLLM's general AD ability remains underexplored due to: (1) MLLMs are pretrained on amounts of data sourced from the Web, these data still have significant gaps with the data in AD scenarios. Moreover, the image-text pairs during pretraining are also not specifically for AD tasks. (2) The current mainstream AD datasets are image-based and not yet suitable for post-training MLLMs. To facilitate MLLM-based general AD research, we present MMR-AD, which is a comprehensive benchmark for both training and evaluating MLLM-based AD models. With MMR-AD, we reveal that the AD performance of current SOTA generalist MLLMs still falls far behind the industrial requirements. Based on MMR-AD, we also propose a baseline model, Anomaly-R1, which is a reasoning-based AD model that learns from the CoT data in MMR-AD and is further enhanced by reinforcement learning. Extensive experiments show that our Anomaly-R1 achieves remarkable improvements over generalist MLLMs in both anomaly detection and localization.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。