Unsupervised Outlier Detection using Memory and Contrastive Learning
arXiv:2107.12642 · doi:10.1109/TIP.2022.3211476
Abstract
Outlier detection is one of the most important processes taken to create good, reliable data in machine learning. The most methods of outlier detection leverage an auxiliary reconstruction task by assuming that outliers are more difficult to be recovered than normal samples (inliers). However, it is not always true, especially for auto-encoder (AE) based models. They may recover certain outliers even 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 feature distance between outliers and inliers. We then propose a framework, MCOD, using a memory module and a contrastive learning module. The memory module constrains the consistency of features, which represent the normal data. The contrastive learning module learns more discriminating features, which boosts the distinction between outliers and inliers. Extensive experiments on four benchmark datasets show that our proposed MCOD achieves a considerable performance and outperforms nine state-of-the-art methods.
References in corpus (10)
- A Simple Framework for Contrastive Learning of Visual Representations
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Deep Learning for Anomaly Detection: A Review
- Improved Baselines with Momentum Contrastive Learning
- Deep Learning for Anomaly Detection: A Survey
- Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning
- CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances
- Deep Nearest Neighbor Anomaly Detection
- Learning and Evaluating Representations for Deep One-class Classification
- Deep Robust Clustering by Contrastive Learning