Recent years have seen a rapid growth in new approaches improving the accuracy of semantic segmentation in a weakly supervised setting, i.e. with only image-level labels available for training. However, this has come at the cost of increased model complexity and sophisticated multi-stage training procedures. This is in contrast to earlier work that used only a single stage − training one segmentation network on image labels − which was abandoned due to inferior segmentation accuracy. In this work, we first define three desirable properties of a weakly supervised method: local consistency, semantic fidelity, and completeness. Using these properties as guidelines, we then develop a segmentation-based network model and a self-supervised training scheme to train for semantic masks from image-level annotations in a single stage. We show that despite its simplicity, our method achieves results that are competitive with significantly more complex pipelines, substantially outperforming earlier single-stage methods.
@article{arxiv.2005.08104,
title = {Single-Stage Semantic Segmentation from Image Labels},
author = {Nikita Araslanov and Stefan Roth},
journal= {arXiv preprint arXiv:2005.08104},
year = {2020}
}
Comments
To appear at CVPR 2020; minor corrections in Eq. (9). Code: https://github.com/visinf/1-stage-wseg