no code implementations • 8 Aug 2022 • Sungpil Kho, Pilhyeon Lee, Wonyoung Lee, Minsong Ki, Hyeran Byun
To this end, previous methods adopt the common pipeline: they generate pseudo masks from class activation maps (CAMs) and use such masks to supervise segmentation networks.
1 code implementation • 25 Sep 2020 • Minsong Ki, Youngjung Uh, Wonyoung Lee, Hyeran Byun
Furthermore, we propose foreground consistency loss that penalizes earlier layers producing noisy attention regarding the later layer as a reference to provide them with a sense of backgroundness.