用自监督方法在无标签数据上识别钢材表面缺陷，准确率达91.3%。
A Masked Autoencoder Approach to Unsupervised Steel Surface Defect Recognition
- 用掩码自编码器学习钢材图像特征，75%区域被遮蔽后重建。
- 预训练后聚类达到91.3%匹配准确率，优于传统无监督方法。
- 适合缺乏标注数据的工业质检场景，可快速部署于真实产线。
钢铁表面缺陷的自动化视觉检测是常见的质量控制任务，其中带标签的缺陷数据稀缺且获取成本高，而未标注的表面图像却非常丰富，这促使了无需类别标签即可学习有效表征的自监督方法的发展。本文采用基于Transformer的掩码自编码器，对钢材表面缺陷进行无监督分组。预训练阶段，输入图像块中75%被随机遮蔽，轻量级解码器从剩余25%可见区域重建被遮蔽部分。编码器与辅助缺陷定位目标联合训练，该目标仅作为训练信号，不参与最终检测评估。解码器达到结构相似性分数0.92和均方误差0.47。预训练编码器提取的特征经UMAP降维后，使用分层聚类进行分组，在六类已知缺陷上达到匈牙利匹配准确率91.3%。
原文摘要 · Abstract (English)
Automated visual inspection of steel surface defects is a recurring quality control task in which labeled defect data is scarce and costly to obtain, while unlabeled surface images are abundant, which motivates self supervised methods that learn useful representations without class labels. A Transformer based Masked Autoencoder is used here to learn representations of steel surface defects for unsupervised grouping. During pretraining, 75% of the input image patches are randomly masked, and a lightweight decoder reconstructs the masked regions from the visible 25%. The encoder is trained jointly with an auxiliary defect localization objective, used only as a training signal and not evaluated as a detector. The decoder reaches a structural similarity score of 0.92 and a mean squared error of 0.47. Features from the pretrained encoder are then clustered using UMAP for dimensionality reduction and Agglomerative clustering, reaching a Hungarian matched accuracy of 91.3% against the six known defect categories.
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。