Unsupervised representation learning based on the deep multi-view ensemble learning

Deep networks have recently achieved great success in feature learning problem on various computer vision applications. Among different approaches in deep learning, unsupervised methods have attracted a lot of attention particularly to problems with limited training data. However, compared with supervised methods, unsupervised deep learning methods usually suffer from lower accuracy and higher computational time. To deal with these problems, we aim to restrict the number of connections between successive layers while enhancing discriminatory power using a data-driven approach. To this end, we propose a novel deep multi-view ensemble model. The structure of each layer is composed of an ensemble of encoders or decoders and mask operations. The multi-view ensemble of encoders or decoders enable the network to benefit from local complementary information and preserve local characteristics in final generated features, while mask operations determine the connections between successive layers. The experimental results on popular datasets indicate the effectiveness and validity of the method in clustering and classification tasks while the processing time is reduced.