Pyramid-based Mamba Multi-class Unsupervised Anomaly Detection
It addresses the problem of small anomaly localization for industrial inspection, representing an incremental advancement over existing CNN and transformer methods.
The paper tackles the challenge of precisely localizing small anomalies in multi-class anomaly detection by introducing a state space model-based pyramidal scanning strategy, achieving improvements of +1% AP for localization and +1% AU-PRO on the MVTec benchmark.
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 at https://github.com/iqbalmlpuniud/Pyramid Mamba.