Class re-activation maps for weakly-supervised semantic segmentation

• Main Authors: CHEN, Zhaozheng, WANG, Tan, WU, Xiongwei, HUA, Xian-Sheng, ZHANG, Hanwang, SUN, Qianru
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2022
• Subjects: class activation maps; weakly supervised learning; semantic segmentation; Databases and Information Systems; Graphics and Human Computer Interfaces
• Online Access: https://ink.library.smu.edu.sg/sis_research/7511; https://ink.library.smu.edu.sg/context/sis_research/article/8514/viewcontent/Chen_Class_Re_Activation_Maps_for_Weakly_Supervised_Semantic_Segmentation_CVPR_2022_paper.pdf
• Institution: Singapore Management University

Extracting class activation maps (CAM) is arguably the most standard step of generating pseudo masks for weakly supervised semantic segmentation (WSSS). Yet, we find that the crux of the unsatisfactory pseudo masks is the binary cross-entropy loss (BCE) widely used in CAM. Specifically, due to the sum...