Graph Regularized Tensor Sparse Coding for Image Representation

TL;DR

This paper introduces a novel graph regularized tensor sparse coding method that preserves spatial structures and geometric properties of images for improved representation, especially in clustering tasks.

Contribution

It proposes a new tensor sparse coding framework with graph regularization that maintains image structures and invariances, enhancing image representation quality.

Findings

Improved image clustering performance.

Preservation of local spatial structures.

Enhanced interpretability of sparse representations.

Abstract

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.