PiCANet: Learning Pixel-Wise Contextual Attention for Saliency Detection

• Published in: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 3089 - 3098
• Main Authors: Liu, Nian, Han, Junwei, Yang, Ming-Hsuan
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2018
• Subjects: Computational modeling; Context modeling; Dogs; Feature extraction; Saliency detection; Task analysis; Visualization

Contexts play an important role in the saliency detection task. However, given a context region, not all contextual information is helpful for the final task. In this paper, we propose a novel pixel-wise contextual attention network, i.e., the PiCANet, to learn to selectively attend to informative c...