A salient object segmentation framework using diffusion-based affinity learning

In this paper, a salient object segmentation framework by using diffusion-based affinity learning and based on absorbing Markov chain (AMC) is proposed. Traditional approaches for structural modeling of images via local information and pairwise similarity graph by using, e.g. Gaussian heat kernel function, are insufficient for capturing the faithful relationships among the regions. According to the AMC principles, the more strong relationships result in lowering the time that a transient node becomes an absorbed one and consequently increases the transition probability between those nodes. To this end, a dense transition probability matrix is constructed based on an affinity matrix which learned using a diffusion process. Computing tensor product of the initial similarity graph with itself provides credible information about inter-relationships of nodes. Since conducting similarity propagation over such a tensor product graph imposes high computational costs, an iterative diffusion process is leveraged that introduces the same complexity as applying traditional diffusion processes on the original graph. As a fundamental benefit, such a process will enhance the accuracy and preciseness of saliency detection. Finally, as a complementary step, the saliency map will be refined by revisiting the saliency value of every single pixel. The experimental results on three major benchmark datasets demonstrate the efficiency of the proposed framework. More specifically, as expected, taking advantage of full learned affinity matrix can significantly improve the precision of the process.