Salient object detection (SOD) is a fundamental computer vision task. Recently, with the revival of deep neural networks, SOD has made great progresses. However, there still exist two thorny issues that cannot be well addressed by existing methods, indistinguishable regions and complex structures. To address these two issues, in this paper we propose a novel deep network for accurate SOD, named CLASS. First, in order to leverage the different advantages of low-level and high-level features, we propose a novel non-local cross-level attention (CLA), which can capture the long-range feature dependencies to enhance the distinction of complete salient object. Second, a novel cross-level supervision (CLS) is designed to learn complementary context for complex structures through pixel-level, region-level and object-level. Then the fine structures and boundaries of salient objects can be well restored. In experiments, with the proposed CLA and CLS, our CLASS net. consistently outperforms 13 state-of-the-art methods on five datasets.

中文翻译：

---

CLASS：显着物体检测的跨级注意和监督

显着目标检测 (SOD) 是一项基本的计算机视觉任务。最近，随着深度神经网络的复兴，SOD取得了长足的进步。然而，仍然存在现有方法无法很好解决的两个棘手问题，不可区分的区域和复杂的结构。为了解决这两个问题，在本文中，我们提出了一种用于精确 SOD 的新型深度网络，名为 CLASS。首先，为了利用低级和高级特征的不同优势，我们提出了一种新颖的非局部跨级注意力（CLA），它可以捕获远程特征依赖性以增强完全显着性的区别目的。其次，一种新颖的跨级监督 (CLS) 旨在通过像素级、区域级和对象级学习复杂结构的互补上下文。然后可以很好地恢复显着物体的精细结构和边界。在实验中，使用建议的 CLA 和 CLS，我们的 CLASS 网络。在五个数据集上始终优于 13 种最先进的方法。