The learning of "Salient Object detection: A Discriminative Regional Feature Integration Approach" (H. Jiang, J. Wang, Z. Yuan, Y. Wu, N. Zheng, and S. Li, in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2013, pp.2083-2090)
Background
- The contrast descriptor, the difference of a region from its surrounding region, which is widely used as saliency (uniqueness) indicators, is not reliable in some images.
- Heuristically hand-crafting special features for saliency may not achieve very good results.
- A salient object is usually formed from a single image segmentation might be not reliable enough
Algorithm review
Integrate the regional contrast, regional property and regional backgroundness descriptors together to form the master saliency map, then fuse the saliency scores across multiple levels, yielding the saliency map.
Model
- Multi-level segmentation
Use the graph-based image segmentation approach to build multi-level segmentationS1,S2,…,Sm .
SuperpixelsR1,R2,…,Rk , saliency feature vector x, a saliency value a = f (x)
- training stage
Across the boundary of the salient object and the background and thus not reliable for training the random forest regressor.
Replace the pairwise similarity over two adjacent regions(Ri,Rj) with a score s(ai,aj)