UniMMAD：基于 MoE 驱动特征解压的统一多模态多类异常检测
UniMMAD: Unified Multi-Modal and Multi-Class Anomaly Detection via MoE-Driven Feature Decompression
把 MoE 稀疏门控用于「通用特征→模态/类别特异特征」的解压式重建，为视觉异常检测提供了一种用单一模型覆盖多模态多类、且避免共享解码路径域干扰的可复用范式；分组动态过滤与 MoE-in-MoE 的约 75% 参数压缩思路也可迁移到其他多域统一建模任务。
原文依据 a Mixture-of-Experts (MoE)-driven feature decompression mechanism, which enables adaptive and disentangled reconstruction tailored to specific domains
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论现有异常检测方法往往将模态与类别视为相互独立的因素。这一范式虽然丰富了异常检测研究方向的发展并催生了许多专用模型，但也导致了解决方案的碎片化与过高的内存开销。此外，基于重建的多类方法通常依赖共享解码路径，难以应对跨域的大幅变化，从而造成正常性边界扭曲、域间干扰以及高误报率。为解决上述局限，我们提出 UniMMAD，一个面向多模态与多类异常检测的统一框架。UniMMAD 的核心是混合专家（MoE）驱动的特征解压机制，它能够针对特定域实现自适应且解耦的重建。该过程由「通用—特异」范式引导。在编码阶段，不同组合的多模态输入被压缩为紧凑的通用特征。编码器引入特征压缩模块以抑制潜变量中的异常、促进跨模态交互并避免捷径学习。在解码阶段，通用特征经由稀疏门控交叉 MoE 解压为模态特异与类别特异的形式，该模块根据输入模态与类别动态选择专家通路。为进一步提升效率，我们设计了分组动态过滤机制与 MoE-in-MoE 结构，在保持稀疏激活与快速推理的同时将 MoE 参数量减少约 75%。UniMMAD 在 9 个异常检测数据集上取得最优性能，覆盖 3 个领域、12 种模态与 66 个类别。代码已公开于 https://github.com/yuanzhao-CVLAB/UniMMAD。
英文原文摘要 1783 字符
Existing anomaly detection methods often treat the modality and class as independent factors. Although this paradigm has enriched the development of AD research branches and produced many specialized models, it has also led to fragmented solutions and excessive memory overhead. Moreover, reconstruction-based multi-class approaches typically rely on shared decoding paths, which struggle to handle large variations across domains, resulting in distorted normality boundaries, domain interference, and high false alarm rates.To address these limitations, we propose UniMMAD, a unified framework for multi-modal and multi-class anomaly detection. At the core of UniMMAD is a Mixture-of-Experts (MoE)-driven feature decompression mechanism, which enables adaptive and disentangled reconstruction tailored to specific domains.This process is guided by a "general - specific" paradigm. In the encoding stage, multi-modal inputs of varying combinations are compressed into compact, general-purpose features. The encoder incorporates a feature compression module to suppress latent anomalies, encourage cross-modal interaction, and avoid shortcut learning.In the decoding stage, the general features are decompressed into modality-specific and class-specific forms via a sparsely-gated cross MoE, which dynamically selects expert pathways based on input modality and class. To further improve efficiency, we design a grouped dynamic filtering mechanism and an MoE-in-MoE structure, reducing MoE parameter usage by approximately 75% while maintaining sparse activation and fast inference. UniMMAD achieves state-of-the-art performance on 9 anomaly detection datasets, spanning 3 fields, 12 modalities, and 66 classes. Code is publicly available at https://github.com/yuanzhao-CVLAB/UniMMAD.