Postdoctoral Station of School of Computer Science and Technology, Harbin University of Science and Technology, Harbin, China.
Department of Electrical Engineering, Wright State University, Dayton, OH, United States of America.
PLoS One. 2018 Jun 20;13(6):e0199141. doi: 10.1371/journal.pone.0199141. eCollection 2018.
Recently, sparse representation, which relies on the underlying assumption that samples can be sparsely represented by their labeled neighbors, has been applied with great success to image classification problems. Through sparse representation-based classification (SRC), the label can be assigned with minimum residual between the sample and its synthetic version with class-specific coding, which means that the coding scheme is the most significant factor for classification accuracy. However, conventional SRC-based coding schemes ignore dependency among the samples, which leads to an undesired result that similar samples may be coded into different categories due to quantization sensitivity. To address this problem, in this paper, a novel approach based on self-supervised sparse representation is proposed for image classification. In the proposed approach, the manifold structure of samples is firstly exploited with low rank representation. Next, the low-rank representation matrix is used to characterize the similarity of samples in order to establish a self-supervised sparse coding model, which aims to preserve the local structure of codings for similar samples. Finally, a numerical algorithm utilizing the alternating direction method of multipliers (ADMM) is developed to obtain the approximate solution. Experiments on several publicly available datasets validate the effectiveness and efficiency of our proposed approach compared with existing state-of-the-art methods.
最近，稀疏表示方法（sparse representation）基于样本可以通过其标记的邻居稀疏表示的基本假设，已成功应用于图像分类问题。通过基于稀疏表示的分类（SRC），可以在样本与其具有特定类别编码的合成版本之间的最小残差下分配标签，这意味着编码方案是分类准确性的最重要因素。然而，传统的基于 SRC 的编码方案忽略了样本之间的依赖性，这导致了一个不理想的结果，即由于量化敏感性，相似的样本可能被编码到不同的类别中。为了解决这个问题，本文提出了一种基于自监督稀疏表示的新方法用于图像分类。在提出的方法中，首先利用低秩表示来挖掘样本的流形结构。接下来，使用低秩表示矩阵来描述样本之间的相似性，以建立一个自监督稀疏编码模型，旨在为相似样本的编码保留局部结构。最后，利用交替方向乘子法（ADMM）开发了一种数值算法来获得近似解。在几个公开可用的数据集上的实验验证了与现有最先进的方法相比，我们提出的方法的有效性和效率。
