Pith

open record

sign in
Browse

arxiv: 2208.03879 · v2 · pith:RJCGR4LV · submitted 2022-08-08 · cs.CV · cs.AI

Clear Memory-Augmented Auto-Encoder for Surface Defect Detection

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 reserved pith:RJCGR4LVrecord.jsonopen to challenge →

classification cs.CV cs.AI
keywords cleardetectiondefectmemory-augmentedmethodsproposeabnormalanomaly
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.