In this paper, we introduce Divide-and-Conquer into the salient object detection (SOD) task to enable the model to learn prior knowledge that is for predicting the saliency map. We design a novel network, Divide-and-Conquer Network (DC-Net) which uses two encoders to solve different subtasks that are conducive to predicting the final saliency map, here is to predict the edge maps with width 4 and location maps of salient objects and then aggregate the feature maps with different semantic information into the decoder to predict the final saliency map. The decoder of DC-Net consists of our newly designed two-level Residual nested-ASPP (ResASPP$^{2}$) modules, which have the ability to capture a large number of different scale features with a small number of convolution operations and have the advantages of maintaining high resolution all the time and being able to obtain a large and compact effective receptive field (ERF). Based on the advantage of Divide-and-Conquer's parallel computing, we use Parallel Acceleration to speed up DC-Net, allowing it to achieve competitive performance on six LR-SOD and five HR-SOD datasets under high efficiency (60 FPS and 55 FPS). Codes and results are available: https://github.com/PiggyJerry/DC-Net.

翻译：本文引入分治策略至显著目标检测任务，使模型能够学习预测显著图的先验知识。我们设计了一种新型网络——分治网络（DC-Net），该网络采用两个编码器分别求解有助于预测最终显著图的子任务：生成宽度为4的边缘图与显著目标位置图，随后将携带不同语义信息的特征图聚合至解码器以预测最终显著图。DC-Net的解码器由我们新设计的两级残差嵌套ASPP模块（ResASPP²）构成，该模块能以较少的卷积操作捕获大量不同尺度的特征，并具备始终保持高分辨率以及获得大而紧凑的有效感受野（ERF）的优势。基于分治策略的并行计算特性，我们采用并行加速技术提升DC-Net速度，使其在高效运行（60FPS与55FPS）条件下，在六个低分辨率显著目标检测（LR-SOD）数据集和五个高分辨率显著目标检测（HR-SOD）数据集上均达到具有竞争力的性能。代码与结果详见：https://github.com/PiggyJerry/DC-Net。