# UniMMAD: Unified Multi-Modal and Multi-Class Anomaly Detection via MoE-Driven Feature Decompression

arXiv: https://arxiv.org/abs/2509.25934 · HTML: https://mlsanity.com/paper/2509.25934/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Vision mixture-of-experts, one of 12 directions in Mixture-of-experts.
- Builds on 9 of its 43 references that are in the map.
- First posted on arXiv 30 Sep 2025.

## Placed in

- Mixture-of-experts / [Vision mixture-of-experts](https://mlsanity.com/moe/vision-mixture-of-experts/)

## Builds on (most cited first, 9 of 9)

- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models](https://mlsanity.com/paper/2401.06066/) (2024)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [From Sparse to Soft Mixtures of Experts](https://mlsanity.com/paper/2308.00951/) (2023)
- [SegGPT: Segmenting Everything In Context](https://mlsanity.com/paper/2304.03284/) (2023)
- [The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localization](https://mlsanity.com/paper/2112.09045/) (2021)
- [MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection](https://mlsanity.com/paper/2404.06564/) (2024)
- [DiAD: A Diffusion-based Framework for Multi-class Anomaly Detection](https://mlsanity.com/paper/2312.06607/) (2023)
- [Spider: A Unified Framework for Context-dependent Concept Segmentation](https://mlsanity.com/paper/2405.01002/) (2024)

## Built on by (most cited first, 3 of 3)

- [Towards an Incremental Unified Multimodal Anomaly Detection: Augmenting Multimodal Denoising From an Information Bottleneck Perspective](https://mlsanity.com/paper/2603.02629/) (2026)
- [MambaADv2: Evolving Duality-enhanced State Space Model for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2606.23126/) (2026)
- [Multi-Modal Anomaly Detection: A Survey](https://mlsanity.com/paper/2608.24937/) (2026)

## Abstract (arXiv)

Existing anomaly detection (AD) 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 to 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 a MoE-in-MoE structure, reducing parameter usage by 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. The source code will be available at https://github.com/yuanzhao-CVLAB/UniMMAD.