Semi-supervised Semantic Segmentation via Strong-weak Dual-branch Network

Meng Yang

Abstract:

While existing works have explored a variety of techniques
to push the envelop of weakly-supervised semantic segmentation, there
is still a significant gap compared to the supervised methods. In realworld application, besides massive amount of weakly-supervised data
there are usually a few available pixel-level annotations, based on which
semi-supervised track becomes a promising way for semantic segmentation. Current methods simply bundle these two different sets of annotations together to train a segmentation network. However, we discover
that such treatment is problematic and achieves even worse results than
just using strong labels, which indicates the misuse of the weak ones.
To fully explore the potential of the weak labels, we propose to impose
separate treatments of strong and weak annotations via a strong-weak
dual-branch network, which discriminates the massive inaccurate weak
supervisions from those strong ones. We design a shared network component to exploit the joint discrimination of strong and weak annotations;
meanwhile, the proposed dual branches separately handle full and weak
supervised learning and effectively eliminate their mutual interference.
This simple architecture requires only slight additional computational
costs during training yet brings significant improvements over the previous methods. Experiments on two standard benchmark datasets show
the effectiveness of the proposed method.