Tensor object classification via multilinear discriminant analysis network
This work addresses tensor object classification for computer vision applications, but it is incremental as it builds on prior deep learning algorithms like LDANet and PCANet.
The paper tackles the problem of classifying multidimensional tensor objects by proposing a multilinear discriminant analysis network (MLDANet), which outperforms existing methods like PCANet and LDANet on the UCF11 database.
This paper proposes a multilinear discriminant analysis network (MLDANet) for the recognition of multidimensional objects, known as tensor objects. The MLDANet is a variation of linear discriminant analysis network (LDANet) and principal component analysis network (PCANet), both of which are the recently proposed deep learning algorithms. The MLDANet consists of three parts: 1) The encoder learned by MLDA from tensor data. 2) Features maps ob-tained from decoder. 3) The use of binary hashing and histogram for feature pooling. A learning algorithm for MLDANet is described. Evaluations on UCF11 database indicate that the proposed MLDANet outperforms the PCANet, LDANet, MPCA + LDA, and MLDA in terms of classification for tensor objects.