ACMamba: Fast Unsupervised Anomaly Detection via An Asymmetrical Consensus State Space Model

2025-04-16

AI Summary

To address the high computational cost and poor real-time deployability of unsupervised anomaly detection in hyperspectral imagery (HSI) caused by high-dimensional data, this paper proposes an asymmetric consensus state-space modeling framework. Methodologically, it introduces (1) a novel region-level asymmetric detection paradigm that jointly optimizes background reconstruction and anomaly compression; (2) a lightweight regional context modeling module built upon the Mamba architecture for efficient long-range dependency capture; and (3) an optimization-driven consensus loss function that integrates state-space modeling to enable effective feature disentanglement. Evaluated on eight benchmark HSI datasets, the method achieves a 3.2× inference speedup while improving average AUC by 2.7% over state-of-the-art approaches—demonstrating superior trade-offs between accuracy and efficiency.

Technology Category

• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Machine Learning: Learning with Manifolds
• Computer Vision: Learning & Optimization for CV

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Unsupervised anomaly detection in hyperspectral images (HSI), aiming to detect unknown targets from backgrounds, is challenging for earth surface monitoring. However, current studies are hindered by steep computational costs due to the high-dimensional property of HSI and dense sampling-based training paradigm, constraining their rapid deployment. Our key observation is that, during training, not all samples within the same homogeneous area are indispensable, whereas ingenious sampling can provide a powerful substitute for reducing costs. Motivated by this, we propose an Asymmetrical Consensus State Space Model (ACMamba) to significantly reduce computational costs without compromising accuracy. Specifically, we design an asymmetrical anomaly detection paradigm that utilizes region-level instances as an efficient alternative to dense pixel-level samples. In this paradigm, a low-cost Mamba-based module is introduced to discover global contextual attributes of regions that are essential for HSI reconstruction. Additionally, we develop a consensus learning strategy from the optimization perspective to simultaneously facilitate background reconstruction and anomaly compression, further alleviating the negative impact of anomaly reconstruction. Theoretical analysis and extensive experiments across eight benchmarks verify the superiority of ACMamba, demonstrating a faster speed and stronger performance over the state-of-the-art.

Problem

• Reducing computational costs in unsupervised HSI anomaly detection
• Replacing dense pixel samples with region-level instances
• Improving speed and accuracy via asymmetrical consensus modeling

Innovation

• Asymmetrical anomaly detection paradigm
• Mamba-based module for global context
• Consensus learning strategy for optimization