论文标题
来自图像标签的单阶段语义分割
Single-Stage Semantic Segmentation from Image Labels
论文作者
论文摘要
近年来，新方法的迅速增长，可以在弱监督的环境中提高语义分割的准确性，即只有图像级标签可用于培训。但是，这是以增加模型复杂性和复杂的多阶段培训程序为代价的。这与早期的工作形成鲜明对比的是，在图像标签上仅使用单个阶段$ - $培训一个细分网络$ - $ - 由于较低的细分精度而被放弃。在这项工作中，我们首先定义了弱监督方法的三个理想属性：局部一致性，语义保真度和完整性。然后，我们将这些属性作为指南，然后开发一个基于细分的网络模型和一个自学的训练方案，以训练单个阶段中图像级注释的语义掩模。我们表明，尽管具有简单性，但我们的方法取得了具有明显复杂管道的竞争性的结果，其表现明显优于早期的单阶段方法。
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.
