首个系统评估异常图像合成方法的基准框架，解决合成数据质量与检测性能的关系难题。
ASBench: Image Anomalies Synthesis Benchmark for Anomaly Detection
- 构建四维评估体系，涵盖跨数据集泛化、合成/真实数据比例等维度
- 发现现有合成方法在不同场景下表现差异大，且合成质量与检测效果关联弱
- 为工业质检中的异常生成提供可复现、可比较的评测标准，适合研究者和工程师
异常检测在制造质量控制中至关重要，但受限于异常样本稀缺和人工标注成本高。尽管异常合成提供了潜在解决方案，现有研究多将合成视为检测框架的附属模块，缺乏对合成算法的系统性评估。当前研究也忽视了异常合成的关键因素，如与检测性能解耦、合成数据的量化分析以及跨场景适应性。为此，我们提出ASBench，首个专注于评估异常合成方法的综合性基准框架。该框架引入四个关键评估维度：(i) 不同数据集与流程间的泛化能力；(ii) 合成数据与真实数据的比例；(iii) 合成图像内在指标与异常检测性能指标之间的相关性；(iv) 混合合成策略。通过大量实验，ASBench不仅揭示了现有合成方法的局限性，还为未来研究方向提供了可操作的洞见。
原文摘要 · Abstract (English)
Anomaly detection plays a pivotal role in manufacturing quality control, yet its application is constrained by limited abnormal samples and high manual annotation costs. While anomaly synthesis offers a promising solution, existing studies predominantly treat anomaly synthesis as an auxiliary component within anomaly detection frameworks, lacking systematic evaluation of anomaly synthesis algorithms. Current research also overlook crucial factors specific to anomaly synthesis, such as decoupling its impact from detection, quantitative analysis of synthetic data and adaptability across different scenarios. To address these limitations, we propose ASBench, the first comprehensive benchmarking framework dedicated to evaluating anomaly synthesis methods. Our framework introduces four critical evaluation dimensions: (i) the generalization performance across different datasets and pipelines (ii) the ratio of synthetic to real data (iii) the correlation between intrinsic metrics of synthesis images and anomaly detection performance metrics , and (iv) strategies for hybrid anomaly synthesis methods. Through extensive experiments, ASBench not only reveals limitations in current anomaly synthesis methods but also provides actionable insights for future research directions in anomaly synthesis
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。