Extracting class activation maps from non-discriminative features as well

• Main Authors: CHEN, Zhaozheng, SUN, Qianru
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2023
• Subjects: Graphics and Human Computer Interfaces
• Online Access: https://ink.library.smu.edu.sg/sis_research/8056; https://ink.library.smu.edu.sg/context/sis_research/article/9059/viewcontent/Chen_Extracting_Class_Activation_Maps_From_Non_Discriminative_Features_As_Well_CVPR_2023_paper.pdf
• Institution: Singapore Management University

Extracting class activation maps (CAM) from a classification model often results in poor coverage on foreground objects, i.e., only the discriminative region (e.g., the “head” of “sheep”) is recognized and the rest (e.g., the “leg” of “sheep”) mistakenly as background. The crux behind is that the we...