CVMar 27, 2017

Graph Regularized Tensor Sparse Coding for Image Representation

arXiv:1703.09342v14 citations
Originality Synthesis-oriented
AI Analysis

This work addresses image representation for clustering tasks, but it appears incremental as it builds on existing tensor and graph regularization techniques.

The paper tackles the problem of preserving spatial structures in images for sparse coding by proposing a graph regularized tensor sparse coding (GTSC) method, which improves image clustering performance as demonstrated experimentally.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes