The learning of "Visual Saliency Detection Based on Multiscale Deep CNN Features" (G.-B. Li, Y.-Z. Yu. IEEE Transactions on Image Processing, Nov, 2016, pp. 5012-5024)
The saliency map is obtained by a random forest regressor using the multiscale high level features and the low level features of artificial selection.
1 Model overview
-
- Segment image using graph-based segmentation, and modify the area according to the bounding box idea.
- High-level feature vector is extracted at three different scales from three CNNs (Alexnet) fed into the two fully connected layers.
- Low-level feature (color and texture) vector is extracted by comparing with boundary background and entire image.
-