Unsupervised Deep Discriminant Analysis Based Clustering
This addresses clustering problems in data analysis, particularly for domains like image processing, but appears incremental as it builds on existing deep learning and discriminant analysis techniques.
The paper tackles unsupervised clustering by developing a deep discriminant analysis method that minimizes intra-cluster discrepancy and maximizes inter-cluster discrepancy, projecting data into a nonlinear low-dimensional space for effective cluster identification, with extensions to incorporate graph information and demonstrated effectiveness on image and non-image datasets.
This work presents an unsupervised deep discriminant analysis for clustering. The method is based on deep neural networks and aims to minimize the intra-cluster discrepancy and maximize the inter-cluster discrepancy in an unsupervised manner. The method is able to project the data into a nonlinear low-dimensional latent space with compact and distinct distribution patterns such that the data clusters can be effectively identified. We further provide an extension of the method such that available graph information can be effectively exploited to improve the clustering performance. Extensive numerical results on image and non-image data with or without graph information demonstrate the effectiveness of the proposed methods.