Salient object detection aims at locating the most conspicuous objects in natural images, which usually acts as a very important pre-processing procedure in many computer vision tasks. In this paper, we propose a simple yet effective Hierarchical U-shape Attention Network (HUAN) to learn a robust mapping function for salient object detection. Firstly, a novel attention mechanism is formulated to improve the well-known U-shape network, in which the memory consumption can be extensively reduced and the mask quality can be significantly improved by the resulting U-shape Attention Network (UAN). Secondly, a novel hierarchical structure is constructed to well bridge the low-level and high-level feature representations between different UANs, in which both the intra-network and inter-network connections are considered to explore the salient patterns from a local to global view. Thirdly, a novel Mask Fusion Network (MFN) is designed to fuse the intermediate prediction results, so as to generate a salient mask which is in higher-quality than any of those inputs. Our HUAN can be trained together with any backbone network in an end-to-end manner, and high-quality masks can be finally learned to represent the salient objects. Extensive experimental results on several benchmark datasets show that our method significantly outperforms most of the state-of-the-art approaches.

中文翻译：

---

用于显着目标检测的分层U形注意网络。

显着物体检测旨在在自然图像中定位最显眼的物体，这通常在许多计算机视觉任务中充当非常重要的预处理程序。在本文中，我们提出了一个简单而有效的层次U形注意网络（HUAN），以学习用于显着目标检测的鲁棒映射功能。首先，提出了一种新颖的注意力机制来改善众所周知的U形网络，该网络可以通过由此产生的U形注意力网络（UAN）大大降低内存消耗，并可以显着提高掩模质量。其次，构建一种新颖的层次结构，以很好地桥接不同UAN之间的低级和高级特征表示，其中，网络内和网络间的连接都被认为是从本地到全局的视角探索显着模式。第三，设计了一种新颖的模板融合网络（MFN）以融合中间预测结果，从而生成质量比任何这些输入都更高的显着模板。我们的HUAN可以以端到端的方式与任何骨干网络一起训练，并且最终可以学习到代表重要对象的高质量蒙版。在一些基准数据集上的大量实验结果表明，我们的方法明显优于大多数最新方法。我们的HUAN可以以端到端的方式与任何骨干网络一起训练，并且最终可以学习到代表重要对象的高质量蒙版。在几个基准数据集上的大量实验结果表明，我们的方法明显优于大多数最新方法。我们的HUAN可以以端到端的方式与任何骨干网络一起训练，并且最终可以学习到代表重要对象的高质量蒙版。在一些基准数据集上的大量实验结果表明，我们的方法明显优于大多数最新方法。