让工业缺陷检测模型可解释并支持用户交互修正。
Interactive Explainable Anomaly Detection for Industrial Settings
- 基于CNN的视觉异常检测，增强输出解释性。
- 提出可交互的近似感知解释框架，提升检测可信度。
- 适合工业质检场景中需人机协同的团队使用。
在工业生产线上识别物体缺陷是质量保证的关键环节。本研究聚焦于基于RGB图像的视觉异常检测。尽管卷积神经网络（CNN）在此任务中表现出高精度，但工业环境中的最终用户无法获得模型决策的额外解释。因此，为模型输出增加解释信息，有助于提升用户对模型的信任，并加快异常检测速度。本文工作包含：(1) 基于CNN的分类模型；(2) 进一步开发一种适用于黑箱分类器的模型无关解释算法；(3) 展示如何构建交互式界面，使用户能够进一步修正模型输出。我们提出了NearCAIPI交互框架，通过用户反馈改进AI性能，并展示该方法如何增强系统的可信度。同时，我们说明了NearCAIPI如何将人类反馈融入交互式处理流程。
原文摘要 · Abstract (English)
Being able to recognise defects in industrial objects is a key element of quality assurance in production lines. Our research focuses on visual anomaly detection in RGB images. Although Convolutional Neural Networks (CNNs) achieve high accuracies in this task, end users in industrial environments receive the model's decisions without additional explanations. Therefore, it is of interest to enrich the model's outputs with further explanations to increase confidence in the model and speed up anomaly detection. In our work, we focus on (1) CNN-based classification models and (2) the further development of a model-agnostic explanation algorithm for black-box classifiers. Additionally, (3) we demonstrate how we can establish an interactive interface that allows users to further correct the model's output. We present our NearCAIPI Interaction Framework, which improves AI through user interaction, and show how this approach increases the system's trustworthiness. We also illustrate how NearCAIPI can integrate human feedback into an interactive process chain.
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。