Salient object detection aims at detecting the most visually distinct objects and producing the corresponding masks. As the cost of pixel-level annotations is high, image tags are usually used as weak supervisions. However, an image tag can only be used to annotate one class of objects. In this paper, we introduce saliency subitizing as the weak supervision since it is class-agnostic. This allows the supervision to be aligned with the property of saliency detection, where the salient objects of an image could be from more than one class. To this end, we propose a model with two modules, Saliency Subitizing Module (SSM) and Saliency Updating Module (SUM). While SSM learns to generate the initial saliency masks using the subitizing information, without the need for any unsupervised methods or some random seeds, SUM helps iteratively refine the generated saliency masks. We conduct extensive experiments on five benchmark datasets. The experimental results show that our method outperforms other weakly-supervised methods and even performs comparable to some fully-supervised methods.

中文翻译：

---

通过显着对象子化进行弱监督显着性检测

显着物体检测旨在检测视觉上最不同的物体并产生相应的掩码。由于像素级注释的成本很高，因此图像标签通常用作弱监督。但是，图像标签只能用于注释一类对象。在本文中，我们将显着性 subitizing 作为弱监督引入，因为它与类别无关。这允许监督与显着性检测的属性保持一致，其中图像的显着对象可能来自多个类。为此，我们提出了一个具有两个模块的模型，显着性子化模块（SSM）和显着性更新模块（SUM）。虽然 SSM 学习使用子化信息生成初始显着性掩码，但不需要任何无监督方法或一些随机种子，SUM 有助于迭代优化生成的显着性掩码。我们对五个基准数据集进行了广泛的实验。实验结果表明，我们的方法优于其他弱监督方法，甚至可以与一些全监督方法相媲美。