Summary of Dmad: Dual Memory Bank For Real-world Anomaly Detection, by Jianlong Hu et al.
DMAD: Dual Memory Bank for Real-World Anomaly Detection
by Jianlong Hu, Xu Chen, Zhenye Gan, Jinlong Peng, Shengchuan Zhang, Jiangning Zhang, Yabiao Wang, Chengjie Wang, Liujuan Cao, Rongrong Ji
First submitted to arxiv on: 19 Mar 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
Summary difficulty | Written by | Summary |
---|---|---|
High | Paper authors | High Difficulty Summary Read the original abstract here |
Medium | GrooveSquid.com (original content) | Medium Difficulty Summary In this research paper, a new framework called Dual Memory bank enhanced representation learning for Anomaly Detection (DMAD) is proposed to tackle the challenge of real-world anomaly detection. The framework handles both unsupervised and semi-supervised scenarios in a unified multi-class setting, using a dual memory bank to calculate feature distance and attention between normal and abnormal patterns. This knowledge is then used to construct an enhanced representation for anomaly score learning. The authors evaluated DMAD on the MVTec-AD and VisA datasets, showing that it surpasses current state-of-the-art methods in handling real-world anomaly detection scenarios. |
Low | GrooveSquid.com (original content) | Low Difficulty Summary In this study, scientists developed a new way to detect unusual things in images or videos called DMAD. It can be used for both unsupervised and semi-supervised learning, which means it can work with different types of data without needing labels every time. The team tested their method on some challenging datasets and found that it performed better than other approaches. |
Keywords
* Artificial intelligence * Anomaly detection * Attention * Representation learning * Semi supervised * Unsupervised