Salient object detection (SOD) is a task that involves identifying and segmenting the most visually prominent object in an image. Existing solutions can accomplish this use a multi-scale feature fusion mechanism to detect the global context of an image. However, as there is no consideration of the structures in the image nor the relations between distant pixels, conventional methods cannot deal with complex scenes effectively. In this paper, we propose an adaptive graph convolution module (AGCM) to overcome these limitations. Prototype features are initially extracted from the input image using a learnable region generation layer that spatially groups features in the image. The prototype features are then refined by propagating information between them based on a graph architecture, where each feature is regarded as a node. Experimental results show that the proposed AGCM dramatically improves the SOD performance both quantitatively and quantitatively.

翻译：显著目标检测（SOD）是一项涉及识别并分割图像中最具视觉显著性的目标的任务。现有解决方案可通过多尺度特征融合机制检测图像的全局上下文来实现该任务。然而，由于未考虑图像内部结构及远距离像素间的关联，传统方法难以有效处理复杂场景。本文提出一种自适应图卷积模块（AGCM）以克服这些局限性。首先，通过可学习的区域生成层从输入图像中提取原型特征，该层对图像中的特征进行空间分组。随后，基于图结构在原型特征间传播信息以对其进行优化，其中每个特征被视为一个节点。实验结果表明，所提出的AGCM在定量和定性评估中均显著提升了SOD性能。