Syed, Shaheen; Anderssen, Kathryn Elizabeth; Stormo, Svein Kristian; Kranz, Mathias (Journal article; Tidsskriftartikkel; Peer reviewed, 2023-02-13)
Fully supervised semantic segmentation models require pixel-level annotations that are costly to obtain. As a remedy, weakly supervised semantic segmentation has been proposed, where image-level labels and class activation maps (CAM) can detect discriminative regions for specific class objects. In this paper, we evaluated several CAM methods applied to different convolutional neural networks (CNN) ...