In recent years, Salient Object Detection (SOD) has shown great success with the achievements of large-scale benchmarks and deep learning techniques. However, existing SOD methods mainly focus on natural images with low-resolutions, e.g., 400×400400\times 400 or less. This drawback hinders them for advanced practical applications, which need high-resolution, detail-aware results. Besides, lacking of the boundary detail and semantic context of salient objects is also a key concern for accurate SOD. To address these issues, in this work we focus on the High-Resolution Salient Object Detection (HRSOD) task. Technically, we propose the first end-to-end learnable framework, named Dual ReFinement Network (DRFNet), for fully automatic HRSOD. More specifically, the proposed DRFNet consists of a shared feature extractor and two effective refinement heads. By decoupling the detail and context information, one refinement head adopts a global-aware feature pyramid. Without increasing too much computational burden, it can boost the spatial detail information, which narrows the gap between high-level semantics and low-level details. In parallel, the other refinement head adopts hybrid dilated convolutional blocks and group-wise upsamplings, which are very efficient in extracting contextual information. Based on the dual refinements, our approach can enlarge receptive fields and obtain more discriminative features from high-resolution images. Experimental results on high-resolution benchmarks (the public DUT-HRSOD and the proposed DAVIS-SOD) demonstrate that our method is not only efficient but also performs more accurate than other state-of-the-arts. Besides, our method generalizes well on typical low-resolution benchmarks.

中文翻译：

---

寻找细节和上下文恶魔：高分辨率显着物体检测


近年来，随着大规模基准测试和深度学习技术的成果，显着目标检测（SOD）取得了巨大成功。然而，现有的SOD方法主要针对低分辨率的自然图像，例如400×400400×400或更小。这一缺点阻碍了它们用于需要高分辨率、细节感知结果的高级实际应用。此外，缺乏显着对象的边界细节和语义上下文也是准确 SOD 的一个关键问题。为了解决这些问题，在这项工作中，我们重点关注高分辨率显着对象检测（HRSOD）任务。从技术上讲，我们提出了第一个端到端可学习框架，名为 Dual ReFinement Network (DRFNet)，用于全自动 HRSOD。更具体地说，所提出的 DRFNet 由一个共享特征提取器和两个有效的细化头组成。通过解耦细节和上下文信息，一个细化头采用了全局感知的特征金字塔。在不增加太多计算负担的情况下，它可以增强空间细节信息，从而缩小高层语义和低层细节之间的差距。同时，另一个细化头采用混合扩张卷积块和分组上采样，这在提取上下文信息方面非常有效。基于双重细化，我们的方法可以扩大感受野并从高分辨率图像中获得更多判别性特征。高分辨率基准（公共 DUT-HRSOD 和提出的 DAVIS-SOD）上的实验结果表明，我们的方法不仅高效，而且比其他最先进的方法执行得更准确。此外，我们的方法可以很好地推广典型的低分辨率基准。