Pyramid-based Mamba Multi-class Unsupervised Anomaly Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Iqbal, Nasar, Martinel, Niki
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915228226158592
author Iqbal, Nasar
Martinel, Niki
author_facet Iqbal, Nasar
Martinel, Niki
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2504_03442
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Pyramid-based Mamba Multi-class Unsupervised Anomaly Detection
Iqbal, Nasar
Martinel, Niki
Computer Vision and Pattern Recognition
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.
title Pyramid-based Mamba Multi-class Unsupervised Anomaly Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.03442