Skip to main content
. Author manuscript; available in PMC: 2021 Oct 1.
Published in final edited form as: IEEE Trans Med Imaging. 2020 Apr 14;39(10):3125–3136. doi: 10.1109/TMI.2020.2987796

Fig. 1.

Fig. 1.

The setting of the proposed attribute-based symmetric MIL framework. The goal is to classify positive and negative bags and to figure out distinctly positive and negative relevant attributes (stripes going from bottom-left to top-right or bottom-right to top-left, respectively) and irrelevant attributes (dotted and wave) in each bag category. The proposed model helps control the relevant instance proportions in the bags.