Affiliation:
1. Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, China
Abstract
The main challenges in reconstruction-based anomaly detection include the breakdown of the generalization gap due to improved fitting capabilities and the overfitting problem arising from simulated defects. To overcome this, we propose a new method called PRFF-AD, which utilizes progressive reconstruction and hierarchical feature fusion. It consists of a reconstructive sub-network and a discriminative sub-network. The former achieves anomaly-free reconstruction while maintaining nominal patterns, and the latter locates defects based on pre- and post-reconstruction information. Given defective samples, we find that adopting a progressive reconstruction approach leads to higher-quality reconstructions without compromising the assumption of a generalization gap. Meanwhile, to alleviate the network’s overfitting of synthetic defects and address the issue of reconstruction errors, we fuse hierarchical features as guidance for discriminating defects. Moreover, with the help of an attention mechanism, the network achieves higher classification and localization accuracy. In addition, we construct a large dataset for packaging chips, named GTanoIC, with 1750 real non-defective samples and 470 real defective samples, and we provide their pixel-level annotations. Evaluation results demonstrate that our method outperforms other reconstruction-based methods on two challenging datasets: MVTec AD and GTanoIC.
Funder
University Key Projects stability fund
Technical Breakthrough projects
Shenzhen Grand Technology Corporation
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference26 articles.
1. Variational autoencoder based anomaly detection using reconstruction probability;An;Spec. Lect. IE,2015
2. Bergmann, P., Löwe, S., Fauser, M., Sattlegger, D., and Steger, C. (2018). Improving unsupervised defect segmentation by applying structural similarity to autoencoders. arXiv.
3. Haselmann, M., Gruber, D.P., and Tabatabai, P. (2018, January 17–20). Anomaly detection using deep learning based image completion. Proceedings of the 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA), Orlando, FL, USA.
4. Anomaly detection of defects on concrete structures with the convolutional autoencoder;Chow;Adv. Eng. Inform.,2020
5. Tang, T.W., Hsu, H., Huang, W.R., and Li, K.M. (2022). Industrial Anomaly Detection with Skip Autoencoder and Deep Feature Extractor. Sensors, 22.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献