English

Clear Memory-Augmented Auto-Encoder for Surface Defect Detection

Computer Vision and Pattern Recognition 2023-02-14 v2 Artificial Intelligence

Abstract

In surface defect detection, due to the extreme imbalance in the number of positive and negative samples, positive-samples-based anomaly detection methods have received more and more attention. Specifically, reconstruction-based methods are the most popular. However, existing methods are either difficult to repair abnormal foregrounds or reconstruct clear backgrounds. Therefore, we propose a clear memory-augmented auto-encoder (CMA-AE). At first, we propose a novel clear memory-augmented module (CMAM), which combines the encoding and memoryencoding in a way of forgetting and inputting, thereby repairing abnormal foregrounds and preserving clear backgrounds. Secondly, a general artificial anomaly generation algorithm (GAAGA) is proposed to simulate anomalies that are as realistic and feature-rich as possible. At last, we propose a novel multi scale feature residual detection method (MSFR) for defect segmentation, which makes the defect location more accurate. Extensive comparison experiments demonstrate that CMA-AE achieves state-of-the-art detection accuracy and shows great potential in industrial applications.

Keywords

Cite

@article{arxiv.2208.03879,
  title  = {Clear Memory-Augmented Auto-Encoder for Surface Defect Detection},
  author = {Wei Luo and Tongzhi Niu and Lixin Tang and Wenyong Yu and Bin Li},
  journal= {arXiv preprint arXiv:2208.03879},
  year   = {2023}
}

Comments

12 pages

R2 v1 2026-06-25T01:33:22.413Z