Robust Tensor Decomposition for Image Representation Based on Generalized Correntropy
This work addresses robustness in image representation for applications like face and digit recognition, but it is incremental as it builds on existing tensor decomposition techniques.
The paper tackled the problem of traditional tensor decomposition methods being sensitive to outliers by proposing a robust method using generalized correntropy, which significantly reduced reconstruction error in face reconstruction and improved accuracies in handwritten digit recognition and facial image clustering.
Traditional tensor decomposition methods, e.g., two dimensional principal component analysis and two dimensional singular value decomposition, that minimize mean square errors, are sensitive to outliers. To overcome this problem, in this paper we propose a new robust tensor decomposition method using generalized correntropy criterion (Corr-Tensor). A Lagrange multiplier method is used to effectively optimize the generalized correntropy objective function in an iterative manner. The Corr-Tensor can effectively improve the robustness of tensor decomposition with the existence of outliers without introducing any extra computational cost. Experimental results demonstrated that the proposed method significantly reduces the reconstruction error on face reconstruction and improves the accuracies on handwritten digit recognition and facial image clustering.