Saliency Detection via Absorbing Markov Chain With Learnt Transition Probability

Abstract

In this paper, we propose a bottom-up saliency model based on absorbing Markov chain (AMC). First, a sparsely connected graph is constructed to capture the local context information of each node. All image boundary nodes and other nodes are, respectively, treated as the absorbing nodes and transient nodes in the absorbing Markov chain. Then, the expected number of times from each transient node to all other transient nodes can be used to represent the saliency value of this node. The absorbed time depends on the weights on the path and their spatial coordinates, which are completely encoded in the transition probability matrix. Considering the importance of this matrix, we adopt different hierarchies of deep features extracted from fully convolutional networks and learn a transition probability matrix, which is called learnt transition probability matrix. Although the performance is significantly promoted, salient objects are not uniformly highlighted very well. To solve this problem, an angular embedding technique is investigated to refine the saliency results. Based on pairwise local orderings, which are produced by the saliency maps of AMC and boundary maps, we rearrange the global orderings (saliency value) of all nodes. Extensive experiments demonstrate that the proposed algorithm outperforms the state-of-the-art methods on six publicly available benchmark data sets.

RGB-T Image Saliency Detection via Collaborative Graph Learning

“…In general, the learnt affinity matrix W could be used to compute the saliency values via semi-supervised methods, such as manifold ranking [15] and absorbing Markov chain [30]. It is worth mentioning that there are some methods taking global cues into account to learn an adaptive graph [8], [31] for saliency detection, but they perform graph learning first then detect saliency regions based on the computed graph. Different from these works, we propose a one-stage method to integrate the computation of saliency values into the process of graph learning.…”

“…While we employ multi-level deep features and structure-fixed graphs to learn a more powerful collaborative graph to better explore intrinsic relations among graph nodes. There are some methods to learn adaptive graphs for saliency detection [8], [31], but they usually perform two steps for saliency computation. Different from these works, we integrate these two steps into a joint process and propose a one-stage method for further boosting their respective performance.…”

“…Challenge-sensitive performance. For analyzing attributesensitive performance of our approach against other methods, we show the quantitative comparisons in In contrast, we only use features trained offline on the datasets used for other tasks such as [8].…”

“…In Table VII, we compare the average running time on the VT821 dataset with other state-of-the-art algorithms. The proposed algorithm costs an average of 2.23s for calculating an RGB-T image pair of 480 × 640 without considering the computational cost of extracting deep features just as [8]. Our speed is not very fast, that's because the W-subproblem and the S-subproblem have the calculation of the inversion operation of a matrix, which are time-consuming.…”

A Salient Object Detection Algorithm Based on Hierarchical Cognitive Mechanism

“…Guo et al [19] found that the boundary effect distorts the area under curve (AUC) and other saliency evaluation indices, and suggested eliminating the boundary effect before salient object detection. Based on the absorption Markov chain, Zhang et al [20] created a novel learning model for salient object detection: the node saliency was defined as the absorption time from each node to the absorption node; the background was defined as the boundary super-pixel. Lu et al [21] proposed a salient object detection method based on error reconstruction: the background superpixel was regarded as the base for sparse and dense representations, and the reconstruction error was used to describe the saliency of image parts.…”