MiniMaxAD: A Lightweight Autoencoder for Feature-Rich Anomaly Detection

arXiv:2405.09933v1 Announce Type: new
Abstract: Previous unsupervised anomaly detection (UAD) methods often struggle with significant intra-class diversity; i.e., a class in a dataset contains multiple subclasses, which we categorize as Feature-Rich Anomaly Detection Datasets (FRADs). This is evident in applications such as unified setting and unmanned supermarket scenarios. To address this challenge, we developed MiniMaxAD: a lightweight autoencoder designed to efficiently compress and memorize extensive information from normal images. Our model utilizes a large kernel convolutional network equipped with a …

abstract anomaly anomaly detection applications arxiv autoencoder challenge class cs.ai cs.cv dataset datasets detection diversity feature multiple struggle supermarket type unsupervised