Image semantic segmentation tasks and methods based on weakly supervised conditions have been proposed and achieve better and better performance in recent years. However, the purpose of these tasks is mainly to simplify the labeling work. In this paper, we establish a new and more challenging task condition: weaklier supervision with one image level annotation per category, which only provides prior knowledge that humans need to recognize new objects, and aims to achieve pixel-level object semantic understanding. In order to solve this problem, a three-stage semantic segmentation framework is put forward, which realizes image level, pixel level, and object common features learning from coarse to fine grade, and finally obtains semantic segmentation results with accurate and complete object regions. Researches on PASCAL VOC 2012 dataset demonstrates the effectiveness of the proposed method, which makes an obvious improvement compared to baselines. Based on fewer supervised information, the method also provides satisfactory performance compared to weakly supervised learning-based methods with complete image-level annotations.

中文翻译：

---

较弱的监督语义分割，每个类别仅具有一个图像级别注释。

近年来，提出了基于弱监督条件的图像语义分割任务和方法，并取得了越来越好的性能。但是，这些任务的目的主要是简化标记工作。在本文中，我们建立了一个新的且更具挑战性的任务条件：较弱的监管，每个类别只有一个图像级别的注释，这仅提供了人类需要识别新对象的先验知识，旨在实现像素级对象的语义理解。为了解决这个问题，提出了一种三阶段语义分割框架，该框架实现了从粗到细的学习，实现了图像水平，像素水平和对象共性，最终获得了准确，完整的对象区域的语义分割结果。对PASCAL VOC 2012数据集的研究证明了该方法的有效性，与基线相比有明显的改进。与较少监督的基于学习的具有完整图像级注释的基于学习的方法相比，该方法基于较少的监督信息，也提供了令人满意的性能。