Improved Autoencoder Model with Memory Module for Anomaly Detection

As a commonly used model for anomaly detection, the autoencoder model for anomaly detection does not train the objective for extracted features, which is a downside of autoencoder model. In addition, it is well known that the autoencoder model has over-prominent reconstruction ability for anomalous data, leading to high false-negative rate. On the other hand, the deep SVDD model firstly extracts features through deep neural network, and then map the extracted features into a hypersphere. However, the deep SVDD model has disadvantages such as feature information loss and feature collapse during training process, leading to a decrease in anomaly detection accuracy. To alleviate such drawbacks mentioned above, in this paper, we propose a novel model, called Improved AutoEncoder model with Memory Module (IAEMM). Specifically, this model jointly learns deep SVDD model and autoencoder model to minimize the overall loss of deep SVDD error and reconstruction error, and add a memory module after encoder to amplify the difference of reconstruction error between normal and abnormal data. The proposed model can well identify abnormal hidden features and mitigate the problem of feature collapse. Experimental results on several datasets confirm the effectiveness and stability of our proposed method.