Learn to Know Unknowns: A Bionic Memory Network for Unsupervised Anomaly Detection

Jiahao Li, Yiqiang Chen, Yunbing XingICLR 2023 · OpenReview

Abstract

Is generalization always beneficial? Over-strong generalization induces the model insensitive to anomalies. Unsupervised anomaly detection requires only unlabeled non-anomalous data to learn and generalize normal patterns, which results in a modest reconstruction error when reconstructing normal instances and a significant reconstruction error when reconstructing anomalies. However, over-strong generalization leads to the indistinguishable reconstruction error of normal instances and anomalies, which means that the model well reconstructs the unknown anomalies, resulting in unnoticeable reconstruction error. Inspired by the cascade structure of the hippocampus and cortex in human brain memory, we proposed a re-representation memory network called Random Forgetting Twin Memory (RFTM) to decompose the latent space and introduce a configurable reintegration mechanism to suppress overgeneralization. RFTM shows striking brain-like memory characteristics, which enables the model to know what it does not know. RFTM has the convenience of a single line of code boosting at the model level without adding any additional extra loss terms at the loss function level. RFTM-based models have achieved state-of-the-art experimental results on different public benchmarks.
BibTeX
@inproceedings{li2023learn,
  author = {Jiahao Li and Yiqiang Chen and Yunbing Xing},
  title = {{Learn to Know Unknowns: A Bionic Memory Network for Unsupervised Anomaly Detection}},
  booktitle = {International Conference on Learning Representations},
  year = {2023},
  url = {https://openreview.net/forum?id=SNzzt94tGzP},
}

Loading related content...

Figure