论文标题
密集的注意流体网络，用于光学遥感图像中的显着对象检测
Dense Attention Fluid Network for Salient Object Detection in Optical Remote Sensing Images
论文作者
论文摘要
尽管自然场景图像（NSIS）的视觉显着性分析取得了显着进步，但光学遥感图像（RSIS）的显着对象检测（SOD）仍然是一个开放且具有挑战性的问题。在本文中，我们提出了一个用于光学RSIS中SOD的端到端致密流体网络（DAFNET）。提出了一个全球环境感知的注意力（GCA）模块以适应性地捕获长期语义上下文关系，并进一步嵌入密集的注意力流体（DAF）结构中，使浅层注意力提示流入深层层以指导高级特征注意力图的产生。具体而言，GCA模块由两个关键组成部分组成，其中全球特征聚合模块从任意两个空间位置实现了显着特征嵌入的相互加强，而级联的Pyramid注意模块可以通过逐步逐步完善级联的Pyramid框架来逐步完善尺度变化问题，从而逐步逐步改进了Chore-to Commod of Commod to Commod of Commode complamid offine offine offine offine commod offine sopline soper-forine shopine commod offine。此外，我们为SOD构建了一个新的且具有挑战性的光学RSI数据集，其中包含2,000张带有像素显着性注释的图像，这是目前最大的公开可用基准。广泛的实验表明，我们提出的DAFNET显着优于现有的最新草皮竞争对手。 https://github.com/rmcong/dafnet_tip20
Despite the remarkable advances in visual saliency analysis for natural scene images (NSIs), salient object detection (SOD) for optical remote sensing images (RSIs) still remains an open and challenging problem. In this paper, we propose an end-to-end Dense Attention Fluid Network (DAFNet) for SOD in optical RSIs. A Global Context-aware Attention (GCA) module is proposed to adaptively capture long-range semantic context relationships, and is further embedded in a Dense Attention Fluid (DAF) structure that enables shallow attention cues flow into deep layers to guide the generation of high-level feature attention maps. Specifically, the GCA module is composed of two key components, where the global feature aggregation module achieves mutual reinforcement of salient feature embeddings from any two spatial locations, and the cascaded pyramid attention module tackles the scale variation issue by building up a cascaded pyramid framework to progressively refine the attention map in a coarse-to-fine manner. In addition, we construct a new and challenging optical RSI dataset for SOD that contains 2,000 images with pixel-wise saliency annotations, which is currently the largest publicly available benchmark. Extensive experiments demonstrate that our proposed DAFNet significantly outperforms the existing state-of-the-art SOD competitors. https://github.com/rmcong/DAFNet_TIP20
