当前位置:
X-MOL 学术
›
Autom. Constr.
›
论文详情
Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
Unsupervised anomaly detection for tile spalling segmentation using synthetic outlier exposure and contrastive learning
Automation in Construction ( IF 9.6 ) Pub Date : 2024-12-30 , DOI: 10.1016/j.autcon.2024.105941
Hai-Wei Wang, Rih-Teng Wu
Automation in Construction ( IF 9.6 ) Pub Date : 2024-12-30 , DOI: 10.1016/j.autcon.2024.105941
Hai-Wei Wang, Rih-Teng Wu
Tile spalling poses significant threats to pedestrians on sidewalks. Recently, deep learning-based approaches have been developed for autonomous building assessments. However, training a supervised model typically requires a large labeled dataset, which is often unavailable in new domain tasks. Moreover, data acquisition and ground-truth labeling are costly. This paper presents an unsupervised framework for anomaly detection of tile spalling. The framework incorporates uncertainty estimation and contrastive learning by training a segmentation model on a source dataset containing known classes, excluding spalling. Spalling is subsequently identified as outlier pixels based on elevated uncertainty scores. Additionally, a synthetic pattern, dubbed “Spalling Craft”, is developed for outlier exposure to further enhance model performance. The proposed approach outperforms state-of-the-art baselines by approximately 18.4%, 46.6%, and 31.7% in AUC, AP, and FPR95 scores, respectively. Compared to supervised learning methods, the framework significantly improves data efficiency while achieving strong performance in tile spalling segmentation.
中文翻译:
使用合成异常值曝光和对比学习进行瓦片剥落分割的无监督异常检测
瓷砖剥落对人行道上的行人构成重大威胁。最近,已经开发了基于深度学习的方法来用于自主建筑评估。但是,训练监督模型通常需要一个大型标记数据集,这在新的域任务中通常不可用。此外,数据采集和真实标记成本高昂。本文提出了一个用于瓦片剥落异常检测的无监督框架。该框架通过在包含已知类(不包括剥落)的源数据集上训练分割模型,将不确定性估计和对比学习相结合。随后,根据升高的不确定性分数将剥落识别为异常像素。此外,还开发了一种名为“剥落工艺”的合成模式,用于异常值暴露,以进一步增强模型性能。所提出的方法在 AUC 、 AP 和 FPR95 评分方面分别比最先进的基线高出约 18.4% 、 46.6% 和 31.7%。与监督学习方法相比,该框架显著提高了数据效率,同时在瓦片剥落分割方面实现了强大的性能。
更新日期:2024-12-30
中文翻译:

使用合成异常值曝光和对比学习进行瓦片剥落分割的无监督异常检测
瓷砖剥落对人行道上的行人构成重大威胁。最近,已经开发了基于深度学习的方法来用于自主建筑评估。但是,训练监督模型通常需要一个大型标记数据集,这在新的域任务中通常不可用。此外,数据采集和真实标记成本高昂。本文提出了一个用于瓦片剥落异常检测的无监督框架。该框架通过在包含已知类(不包括剥落)的源数据集上训练分割模型,将不确定性估计和对比学习相结合。随后,根据升高的不确定性分数将剥落识别为异常像素。此外,还开发了一种名为“剥落工艺”的合成模式,用于异常值暴露,以进一步增强模型性能。所提出的方法在 AUC 、 AP 和 FPR95 评分方面分别比最先进的基线高出约 18.4% 、 46.6% 和 31.7%。与监督学习方法相比,该框架显著提高了数据效率,同时在瓦片剥落分割方面实现了强大的性能。