Benchmarking Suite for Synthetic Aperture Radar Imagery Anomaly Detection (SARIAD) Algorithms

2025-04-10

AI Summary

The synthetic aperture radar (SAR) image anomaly detection community lacks standardized benchmarks and evaluation tools, hindering fair comparison and reproducibility. Method: This paper introduces SARIAD—the first open-source benchmark suite for SAR anomaly detection. It systematically integrates six publicly available SAR datasets, implements unified preprocessing, multi-scale feature modeling, and unsupervised/self-supervised anomaly scoring pipelines. It proposes SAR-specific metrics—including SAR-AUC and mask IoU—along with dedicated visualization tools, and deeply integrates the Anomalib framework to enable end-to-end reproducible experiments. Contribution/Results: SARIAD fills a critical gap in standardized evaluation for SAR anomaly detection, providing an extensible platform that already incorporates 12 state-of-the-art algorithms. It significantly enhances method comparability, experimental reproducibility, and collaborative research efficiency, and has gained widespread adoption on GitHub.

Technology Category

• Computer Vision: Image and Video Retrieval
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Machine Learning: Evaluation and Analysis

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Anomaly detection is a key research challenge in computer vision and machine learning with applications in many fields from quality control to radar imaging. In radar imaging, specifically synthetic aperture radar (SAR), anomaly detection can be used for the classification, detection, and segmentation of objects of interest. However, there is no method for developing and benchmarking these methods on SAR imagery. To address this issue, we introduce SAR imagery anomaly detection (SARIAD). In conjunction with Anomalib, a deep-learning library for anomaly detection, SARIAD provides a comprehensive suite of algorithms and datasets for assessing and developing anomaly detection approaches on SAR imagery. SARIAD specifically integrates multiple SAR datasets along with tools to effectively apply various anomaly detection algorithms to SAR imagery. Several anomaly detection metrics and visualizations are available. Overall, SARIAD acts as a central package for benchmarking SAR models and datasets to allow for reproducible research in the field of anomaly detection in SAR imagery. This package is publicly available: https://github.com/Advanced-Vision-and-Learning-Lab/SARIAD.

Problem

• Lack of benchmarking tools for SAR anomaly detection algorithms
• Need for standardized SAR datasets and evaluation metrics
• Integration of deep learning with SAR imagery analysis

Innovation

• Integrates multiple SAR datasets for anomaly detection
• Combines with Anomalib deep-learning library
• Provides benchmarking tools and metrics