Based on this attribute homophily rate, we propose a Diverse Message Passing (DMP) framework, which specifies every attribute propagation weight on each edge.
For these matters, we propose the following designs to push the performance to new state-of-art: (i) Coefficient of Variation Smoothing to smooth the CAMs adaptively; (ii) Proportional Pseudo-mask Generation to project the expanded CAMs to pseudo-mask based on a new metric indicating the importance of each class on each location, instead of the scores trained from binary classifiers.
Ranked #1 on Weakly-Supervised Semantic Segmentation on PASCAL VOC 2012 val (mIoU metric)
Our method can be used to prune any structures including those with coupled channels.
Multi-task learning (MTL) has been widely used in representation learning.