Anomaly Detection via Progressive Reconstruction and Hierarchical Feature Fusion

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.

Image Segmentation of Fiducial Marks with Complex Backgrounds Based on the mARU-Net

“…In addition, the application of deep learning to defect detection is extensive when adapting to industrial scenarios, while refactor-based anomaly detection methods have been widely studied [29,30]. Fei Liu et al [31] proposed a new method which utilized progressive reconstruction and hierarchical feature fusion to detect packaging chips. Bing Tu et al [32] established a new hyperspectral anomaly detection method based on reconstruction fusion, which improved robust detection performances.…”