arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1703.09342cs.CV
收藏

图正则化张量稀疏编码的图像表示

Graph Regularized Tensor Sparse Coding for Image Representation

Shanghai Jiao Tong University(上海交通大学);Columbia University(哥伦比亚大学)

Fei Jiang, Xiao-Yang Liu, Hongtao Lu, Ruimin Shen

摘要:

稀疏编码是一种无监督学习方法,近年来受到越来越多的关注。然而,传统的SC矢量化的输入图像,这破坏了固有的空间结构的图像。在本文中,我们提出了一种新的图正则化张量稀疏编码(GTSC)的图像表示。GTSC通过采用新提出的管张量表示来保持图像中基本结构的局部邻近性。同时,它考虑了固有的几何特性,通过施加图正则化,已成功地应用于揭示图像数据的几何分布。此外,GTSC返回的稀疏表示具有更好的物理解释作为关键操作(即,循环卷积)保持了移位不变性。图像聚类实验结果表明了该方法的有效性。

英文摘要:

Sparse coding (SC) is an unsupervised learning scheme that has received an increasing amount of interests in recent years. However, conventional SC vectorizes the input images, which destructs the intrinsic spatial structures of the images. In this paper, we propose a novel graph regularized tensor sparse coding (GTSC) for image representation. GTSC preserves the local proximity of elementary structures in the image by adopting the newly proposed tubal-tensor representation. Simultaneously, it considers the intrinsic geometric properties by imposing graph regularization that has been successfully applied to uncover the geometric distribution for the image data. Moreover, the returned sparse representations by GTSC have better physical explanations as the key operation (i.e., circular convolution) in the tubal-tensor model preserves the shifting invariance property. Experimental results on image clustering demonstrate the effectiveness of the proposed scheme.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑