A Co-saliency Model of Image Pairs

In this paper, we introduce a method to detect co-saliency from an image pair that may have some objects in common. The co-saliency is modeled as a linear combination of the single-image saliency map (SISM) and the multi-image  saliency map (MISM). The first term is designed to describe the local attention, which is computed by using three saliency detection techniques available in literature. To compute the MISM, a co-multilayer graph is constructed by dividing the image pair into a spatial pyramid representation. Each node in the graph is described by two types of visual descriptors, which are extracted from a representation of some aspects of local appearance, e.g., color and texture properties. In order to evaluate the similarity between two nodes, we employ a normalized single-pair SimRank algorithm to compute the similarity score. Experimental evaluation on a number of image pairs demonstrates the good performance of the proposed method on the co-saliency detection task.

Hongliang Li, King Ngi Ngan, "A Co-saliency Model of Image Pairs," IEEE Transactions on Image Processing, vol. 20, no. 12, pp. 3365-3375,  2011.  [PDF

Experimental results for single objects. (a)-(b) and (e)-(f): Original image pairs. (c)-(d) and (g)-(h): Results by our method.

Experimental results for multiple objects. (a)-(b): Original image pairs. (c)-(d): Results by our method.
1. Ground truth Used for Comparison
   105 test image pairs and ground truth masks can be downloaded from here
2. Our co-saliency results for 105 test image pairs can be downloaded from here
3. Source Code (MATLAB)
   Source code can be downloaded from here
Note: Test images and ground truth masks have been updated. Each dataset includes 210 images that are consistent with our published paper.
This work was partially supported by NSFC (No.60972109), the Program for New Century Excellent Talents in University (NCET-08-0090) and Sichuan Province Science Foundation for Youths (No. 2010JQ0003).