Geodesic Weighted Bayesian Model for Salient Object Detection


In recent years, a variety of salient object detection methods under Bayesian framework have been proposed and many achieved state of the art. However, those ignore spatial relationships and thus background regions similar to the objects are also highlighted. In this paper, we propose a novel geodesic weighted Bayesian model to address this issue. We consider spatial relationships by attaching more importance to regions which are more likely to be parts of a salient object, thus suppressing background regions. First, we learn a combined similarity via multiple features to measure similarity of adjacent regions. Then, we apply the combined similarity as edge weight to construct an undirected weighted graph and compute geodesic distance. Last, we utilize the geodesic distance to weight the observation likelihood to infer a more precise saliency map. Experiments on several benchmark datasets demonstrate the effectiveness of our model.


ICIP Oral Paper (PDF)
  author    = {Wang, Xiang and Ma, Huimin and Chen, Xiaozhi},
  title     = {Geodesic Weighted {B}ayesian Model for Salient Object Detection},
  booktitle = {IEEE ICIP},
  year      = {2015},
  pages	    = {397-401},
  doi	    = {10.1109/ICIP.2015.7350828}


We test our method on two standard benchmark datasets: ASD and CSSD. ASD which contains 1000 images is widely used and relatively simple while CSSD containing 200 images which is more challenging.

Dummy Image

Comparison of different methods with their improved versions (*). The first row are tested on ASD and the second are on CSSD. The first two columns show the improvement of PR curves and the last column shows the improvement of F-measure.