MaskAD: Parallel Masked Autoencoder for Multi-class Unsupervised Anomaly Detection

Ruiying Lu; Gang Liu; Kang Li; Long Tian; Junwei Zhang

AAAI 2026technical0 citations

MaskAD: Parallel Masked Autoencoder for Multi-class Unsupervised Anomaly Detection

Ruiying Lu, Gang Liu, Kang Li, Long Tian, Junwei Zhang

Abstract

Multi-class unsupervised anomaly detection endeavors to establish a unified model capable of identifying anomalies across multiple classes when only normal data is accessible. However, widely employed reconstruction-based networks often struggle with the

BibTeX

@inproceedings{aaai2026_maskadparallelma,
  title = {MaskAD: Parallel Masked Autoencoder for Multi-class Unsupervised Anomaly Detection},
  author = {Ruiying Lu and Gang Liu and Kang Li and Long Tian and Junwei Zhang},
  booktitle = {AAAI 2026},
  year = {2026}
}