The extensive research leveraging RGB-D information has been exploited in salient object detection. However, salient visual cues appear in various scales and resolutions of RGB images due to semantic gaps at different feature levels. Meanwhile, similar salient patterns are available in cross-modal depth images as well as multi-scale versions. Cross-modal fusion and multi-scale refinement are still an open problem in RGB-D salient object detection task. In this paper, we begin by introducing top-down and bottom-up iterative refinement architecture to leverage multi-scale features, and then devise attention based fusion module (ABF) to address on cross-modal correlation. We conduct extensive experiments on seven public datasets. The experimental results show the effectiveness of our devised method
翻译:利用RGB-D信息的广泛研究在显著的物体探测中得到了利用,然而,由于不同特征层次的语义差距,在RGB图像的不同尺度和分辨率中出现了明显的视觉提示;同时,跨模式深度图像和多尺度版本中也有类似的显著模式;在RGB-D显著物体探测任务中,跨模式融合和多尺度改进仍然是一个尚未解决的问题。在本文件中,我们首先采用自上而下和自下而上的迭接性完善结构来利用多尺度的特征,然后设计基于关注的聚合模块(ABF)来应对跨模式的相互关系。我们在七个公共数据集上进行了广泛的实验。实验结果显示了我们设计的方法的有效性。