The Convolutional Neural Networks (CNNs) with encoder-decoder architecture has shown powerful ability in semantic segmentation and it has also been applied in saliency detection. In most researches, the parameters of the backbone network which have been pre-trained on the ImageNet dataset will be retrained using the new training dataset to let CNNs adapt to the new task better. But the retraining will weaken generalization of the pre-trained backbone network and result in over-fitting, especially when the scale of the new training data is not very large. To make a balance between generalization and precision, and to further improve the performance of the CNNs with encoder-decoder architecture in salient object detection, we proposed a framework with enhanced backbone network (BENet). A encoder with structure of dual backbone networks (DBNs) is adopted in BENet to extract more diverse feature maps. In addition, BENet includes a connection module based on improved Res2Net to efficiently fuse feature maps from the two backbone networks and a decoder based on weighted multi-scale feedback module (WMFM) to perform synchronous learning. Our approach is extensively evaluated on six public datasets, and experimental results show significant and consistent improvements over the state-of-the-art methods without any additional supervision.

具有编码器-解码器体系结构的卷积神经网络（CNN）在语义分割方面显示出强大的功能，并且已在显着性检测中得到应用。在大多数研究中，将使用新的训练数据集对在ImageNet数据集上预先训练的骨干网参数进行重新训练，以使CNN更好地适应新任务。但是，重新训练会削弱预训练骨干网络的泛化能力，并导致过度拟合，尤其是在新训练数据的规模不是很大的情况下。为了在泛化和精度之间取得平衡，并进一步提高带有编码器-解码器体系结构的CNN在显着目标检测中的性能，我们提出了一种具有增强型骨干网（BENet）的框架。BENet中采用具有双主干网（DBN）结构的编码器来提取更多不同的特征图。此外，Benet包括一个基于改进的Res2Net的连接模块，以有效地融合来自两个骨干网络的特征图；以及一个基于加权多尺度反馈模块（WMFM）的解码器，以执行同步学习。我们的方法在六个公共数据集上得到了广泛的评估，实验结果表明，在没有任何其他监督的情况下，与现有技术相比，已有了显着而一致的改进。