College of Information Science and Engineering, Xinjiang University, Urumqi 830046, China.
Sensors (Basel). 2022 Jun 14;22(12):4490. doi: 10.3390/s22124490.
Different feature learning strategies have enhanced performance in recent deep neural network-based salient object detection. Multi-scale strategy and residual learning strategies are two types of multi-scale learning strategies. However, there are still some problems, such as the inability to effectively utilize multi-scale feature information and the lack of fine object boundaries. We propose a feature refined network (FRNet) to overcome the problems mentioned, which includes a novel feature learning strategy that combines the multi-scale and residual learning strategies to generate the final saliency prediction. We introduce the spatial and channel 'squeeze and excitation' blocks (scSE) at the side outputs of the backbone. It allows the network to concentrate more on saliency regions at various scales. Then, we propose the adaptive feature fusion module (AFFM), which efficiently fuses multi-scale feature information in order to predict superior saliency maps. Finally, to supervise network learning of more information on object boundaries, we propose a hybrid loss that contains four fundamental losses and combines properties of diverse losses. Comprehensive experiments demonstrate the effectiveness of the FRNet on five datasets, with competitive results when compared to other relevant approaches.
不同的特征学习策略在最近基于深度神经网络的显著目标检测中提高了性能。多尺度策略和残差学习策略是两种类型的多尺度学习策略。然而，仍然存在一些问题，例如无法有效地利用多尺度特征信息和缺乏精细的目标边界。我们提出了一种特征细化网络（FRNet）来克服所提到的问题，它包括一种新颖的特征学习策略，该策略结合了多尺度和残差学习策略来生成最终的显著预测。我们在骨干网的侧输出引入了空间和通道“挤压和激励”块（scSE）。它使网络能够在各种尺度上更加关注显著区域。然后，我们提出了自适应特征融合模块（AFFM），它有效地融合了多尺度特征信息，以便预测出更好的显著图。最后，为了监督网络对对象边界的更多信息进行学习，我们提出了一种混合损失，它包含四个基本损失，并结合了不同损失的特性。综合实验证明了 FRNet 在五个数据集上的有效性，与其他相关方法相比，具有竞争力的结果。
