Salient Object Detection via Bootstrap Learning Supplementary Materials

In Figure 2(a), we provide the Precision and Recall (P-R) curves of the proposed bootstrap learning algorithm when each of the three features (RGB, CIELab and LBP) is removed, respectively. These results show that each feature contributes to detect salient objects. In addition, we show the P-R curve of the proposed method in comparison with those of single-scale methods in Figure 2(b), which demonstrates the effects of the multiscale integration in the proposed method. These results show that the efficiency of the proposed method could be largely improved by adopting only single scale at the expense of some decrease in accuracy.