Unsupervised Outlier Detection Using Memory and Contrastive Learning

doi:10.1109/TIP.2022.3211476

Unsupervised Outlier Detection Using Memory and Contrastive Learning

2022-01-01

15

OA

AI

DOI：10.1109/TIP.2022.3211476

Original

Original request for help

Save

Abstract

En 中文

Outlier detection is to separate anomalous data from inliers in the dataset. Recently, the most deep learning methods of outlier detection leverage an auxiliary reconstruction task by assuming that outliers are more difficult to recover than normal samples (inliers). However, it is not always true in deep auto-encoder (AE) based models. The auto-encoder based detectors may recover certain outliers even if outliers are not in the training data, because they do not constrain the feature learning. Instead, we think outlier detection can be done in the feature space by measuring the distance between outliers' features and the consistency feature of inliers. To achieve this, we propose an unsupervised outlier detection method using a memory module and a contrastive learning module (MCOD). The memory module constrains the consistency of features, which merely represent the normal data. The contrastive learning module learns more discriminative features, which boosts the distinction between outliers and inliers. Extensive experiments on four benchmark datasets show that our proposed MCOD performs well and outperforms eleven state-of-the-art methods.

Keywords:

Feature extraction

Prototypes

Image reconstruction

Training

Memory modules

Anomaly detection

Detectors

Anomaly detection

contrastive learning

memory module

deep clustering

unsupervised learning

Unsupervised Outlier Detection Using Memory and Contrastive Learning

Abstract

Journal

Organization