Coarse-to-Fine Salient Object Detection with Low-Rank Matrix Recovery
This work addresses a specific limitation in saliency detection for computer vision applications, representing an incremental improvement over existing LRMR methods.
The paper tackles the problem of scattered or incomplete saliency maps in Low-Rank Matrix Recovery (LRMR)-based saliency detection by introducing a coarse-to-fine framework that refines saliency values to sharpen boundaries and preserve object entirety, achieving superior results on three benchmark datasets, especially for images with multiple objects.
Low-Rank Matrix Recovery (LRMR) has recently been applied to saliency detection by decomposing image features into a low-rank component associated with background and a sparse component associated with visual salient regions. Despite its great potential, existing LRMR-based saliency detection methods seldom consider the inter-relationship among elements within these two components, thus are prone to generating scattered or incomplete saliency maps. In this paper, we introduce a novel and efficient LRMR-based saliency detection model under a coarse-to-fine framework to circumvent this limitation. First, we roughly measure the saliency of image regions with a baseline LRMR model that integrates a $\ell_1$-norm sparsity constraint and a Laplacian regularization smooth term. Given samples from the coarse saliency map, we then learn a projection that maps image features to refined saliency values, to significantly sharpen the object boundaries and to preserve the object entirety. We evaluate our framework against existing LRMR-based methods on three benchmark datasets. Experimental results validate the superiority of our method as well as the effectiveness of our suggested coarse-to-fine framework, especially for images containing multiple objects.