Search Results for author:
Found 2 papers, 0 papers with code
Saliency guided deep network for weakly-supervised image segmentation
Classification activation mapping is a common method which can be used to generate high-precise object location cues.
Self-Attention Recurrent Network for Saliency Detection
Therefore, the network generates elaborate saliency maps by enhancing local and global information of feature maps in different layers.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
