Progressive self-guided loss for salient object detection

• Main Authors: Yang, Sheng, Lin, Weisi, Lin, Guosheng, Jiang, Qiuping, Liu, Zichuan
• Other Authors: School of Computer Science and Engineering
• Format: Article
• Language: English
• Published: 2022
• Subjects: Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision; Salient Object Detection; Deep Learning
• Online Access: https://hdl.handle.net/10356/155736
• Institution: Nanyang Technological University

We present a simple yet effective progressive self-guided loss function to facilitate deep learning-based salient object detection (SOD) in images. The saliency maps produced by the most relevant works still suffer from incomplete predictions due to the internal complexity of salient objects. Our pr...