Sparse Tensor Auto-Encoder for Saliency Detection

Abstract

In this paper a new Sparse Tensor Auto-Encoder (STAE) model is proposed to learn a latent and discriminative feature representations for saliency detection. By formulating the background patches as holistic high-dimensional tensors and learning multi-dimensional dictionary to code image patches, the coding error can precisely reveal the difference between salient object and background. Then a saliency map can be derived by a subsequent refinement of the representation errors of patches via image segmentation. Several benchmark datasets are used to verify the effectiveness of the proposed method. The results show that the proposed STAE can accurately locate saliency region and outperform its counterparts.