Salient Object Detection Via Attention-Aware Cascaded Bottom-up Feature Aggregation

Fully convolutional neural network-based salient object detection has recently achieved great success with its performance benefits from the effective use of multi-layer features. Based on this, most of the existing saliency detectors design complex network structures to fuse the multi-level features of the backbone feature network. However, information in different layer play different roles in saliency object detection, how to integrate them is still an open problem. In this paper, a cascaded bottom-up feature aggregation module is designed to retain and strengthen more spatial details in the low-level features, and embed attention mechanism in the process of feature aggregation to filter more effective features. Extensive experiments show that the proposed networks can consistently improve saliency detection performance. The experimental results on five public datasets prove that this network is competitive in saliency detection.