GSM: Global Semantic Memory
Year: 2025
Type: article
Abstract: Unsupervised anomaly detection is to detect previously unseen rare samples without any prior knowledge about them. With the emergence of deep learning, many methods employ normal data reconstruction to train detection models, which is expected to yield relatively large errors when reconstructing anomalies. However, recent studies find that anomalies can be overgeneralized, resulting in reconstruction errors as small as normal samples. In this paper, we examine the anomaly overgeneralization problem and propose global semantic information learning. Normal and anomalous samples may share the same local feature such as textures, edges, and corners, but have separability at the global semantic level. To address this, we propose the global semantic memory with novel cascade architecture designed to capture global semantic information in the latent space and introduce a configurable sparsification and random forgetting mechanism. Our proposed method achieves state-of-the-art experimental results on different public benchmarks, without the introduction of any additional auxiliary loss.
Source: Pattern Recognition
Authors: Jiahao Li, Yiqiang Chen, Yunbing Xing, Yang Gu, Xiangyuan Lan
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Estimated APC paid: $2,590
Funders: Peng Cheng Laboratory, Natural Science Foundation of Hunan Province, Youth Innovation Promotion Association of the Chinese Academy of Sciences, Beijing Municipal Science and Technology Commission, Science and Technology Program of Hunan Province, Institute of Computing Technology, Chinese Academy of Sciences
OpenAlex ID: W4411371859