Branches Mutual Promotion for End-to-End Weakly Supervised Semantic Segmentation. (arXiv:2308.04949v1 [cs.CV])

End-to-end weakly supervised semantic segmentation aims at optimizing a
segmentation model in a single-stage training process based on only image
annotations. Existing methods adopt an online-trained classification branch to
provide pseudo annotations for supervising the segmentation branch. However,
this strategy makes the classification branch dominate the whole concurrent
training process, hindering these two branches from assisting each other. In
our work, we treat these two branches equally by viewing them as diverse ways
to generate the segmentation map, and add …

annotations arxiv classification image process promotion segmentation semantic stage strategy training