Qihao Lin, Jinyu Cai and Genggeng Liu, Fuzhou University, China
High-dimensional of image data is an obstacle for clustering. One of methods to solve it is feature representation learning. However, if the image is distorted or suffers from the influence of noise, the extraction of effective features may be difficult. In this paper, an end-to-end feature learning model is proposed to extract denoising low-dimensional representations from distorted images, and these denoising features are evaluated by comparing with several feature representation methods in clustering task. First, some related works about classical feature learning are introduced. Then the architecture and working mechanism of denoising feature learning model are presented. As the structural characteristics of this model, it can obtain essential information from image to decrease reconstruction error. When facing with corrupted data, it also runs a robust clustering result. Finally, compared to other unsupervised feature learning methods, extensive experiments demonstrate that the obtained feature representations by proposed model run a competitive clustering performance. The low-dimensional representations can replace the original datasets primely.
Unsupervised Learning, Feature Representation, Auto-encoder, Clustering.