Salient Object Detection by Pyramid Networks with Gating

In the paper, we propose a salient object detection architecture named as Gating for Double Pyramid Networks (GDPNet). It consists of two pyramid structures: Feature Pyramid Network (FPN) and Pyramid Pooling Module (PPM). FPN has the capability of capturing the inherent multi-scale and pyramid hierarchy, while PPM can exploit the global context information by different-region-based context aggregation. It is known that the irrelevant information corresponding to non-salient objects or background may deteriorate the performance of the model. We introduce two gating strategies, i.e., Cross-Gating for FPN and Single-Gating for PPM, to suppress the incurred irrelevant information in hidden features. Our proposed approach achieves state-of-the-art performance on five benchmark datasets, which demonstrates the effectiveness and robust feature extraction capability of proposed GDPNet.