Single-Stage Semantic Segmentation from Image Labels

TL;DR

This paper introduces a simple yet effective single-stage method for weakly supervised semantic segmentation using only image labels, achieving competitive results without complex multi-stage training.

Contribution

The authors propose a novel single-stage network and self-supervised training scheme that meet key properties, outperforming previous single-stage approaches in weakly supervised segmentation.

Findings

Achieves competitive segmentation accuracy with a simple single-stage approach.

Outperforms earlier single-stage methods significantly.

Maintains local consistency, semantic fidelity, and completeness in segmentation.

Abstract

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.