Peanet: The products of experts autoencoder for abnormal detection

Recent researches have shown great progress in abnormal detection with the application of deep neural network. However, those works tend to solve the task concentrating on homogeneous features or with a decoupled model that combines features inefficiently. In this paper, we propose a method for abnormal detection that learns different features' distributions in low-dimensionalities and combines them in an efficient way. The main architecture of our work consists of a two-stream AutoEncoder and LSTM architecture model to get the compressed low-dimensional spatial and temporal features respectively. Instead of standard Expectation-Maximization algorithm, we further design two estimation network to estimate probability densities and combine them with the Products of Experts. In addition, the experiments of our method on different dataset deliver on-par or superior performance compared to state-of-the-art methods in one-class and abnormal detection settings.