Bootstrapping the performance of webly supervised semantic segmentation

• Main Authors: Shen, Tong, Lin, Guosheng, Shen, Chunhua, Reid, Ian
• Other Authors: School of Computer Science and Engineering
• Format: Conference or Workshop Item
• Language: English
• Published: 2020
• Subjects: Engineering::Computer science and engineering; Training; Image Segmentation
• Online Access: https://hdl.handle.net/10356/142802
• Institution: Nanyang Technological University

Fully supervised methods for semantic segmentation require pixel-level class masks to train, the creation of which is expensive in terms of manual labour and time. In this work, we focus on weak supervision, developing a method for training a high-quality pixel-level classifier for semantic segmenta...