Pyramid-based Mamba Multi-class Unsupervised Anomaly Detection

Recent advances in convolutional neural networks (CNNs) and transformer-based methods have improved anomaly detection and localization, but challenges persist in precisely localizing small anomalies. While CNNs face limitations in capturing long-range dependencies, transformer architectures often suffer from substantial computational overheads. We introduce a state space model (SSM)-based Pyramidal Scanning Strategy (PSS) for multi-class anomaly detection and localization--a novel approach designed to address the challenge of small anomaly localization. Our method captures fine-grained details at multiple scales by integrating the PSS with a pre-trained encoder for multi-scale feature extraction and a feature-level synthetic anomaly generator. An improvement of $+1\%$ AP for multi-class anomaly localization and a +$1\%$ increase in AU-PRO on MVTec benchmark demonstrate our method's superiority in precise anomaly localization across diverse industrial scenarios. The code is available atthis https URLMamba.

@article{iqbal2025_2504.03442,
  title={ Pyramid-based Mamba Multi-class Unsupervised Anomaly Detection },
  author={ Nasar Iqbal and Niki Martinel },
  journal={arXiv preprint arXiv:2504.03442},
  year={ 2025 }
}