In the wake of recent advances in joint clustering and deep learning, we introduce the Deep Embedded Self-Organizing Map, a model that jointly learns representations and the code vectors of a self-organizing map.
DIMENSIONALITY REDUCTION REPRESENTATION LEARNING SELF-ORGANIZED CLUSTERING
The proposed model is able to boost the performance of data clustering, semisupervised classification, and data recovery significantly, primarily due to two key factors: 1) enhanced low-rank recovery by exploiting the graph smoothness assumption, 2) improved graph construction by exploiting clean data recovered by robust PCA.
GRAPH CONSTRUCTION GRAPH LEARNING IMAGE/DOCUMENT CLUSTERING IMAGE SHADOW REMOVAL OBJECT RECOGNITION SHADOW REMOVAL VIDEO BACKGROUND SUBTRACTION