An Important Pick-and-Pass Gated Refinement Network for Salient Object Detection in Optical Remote Sensing Images

Salient object detection in optical remote sensing images (ORSI-SOD) is a very challenging task due to the complex scale, shape, details, uncertainty of the predicted location of the object, etc. In this article, we propose a novel important pick-and-pass gated refinement network model for SOD in ORSIs, named IP2GRNet, including a detail refinement stage and a feature pick-and-pass refinement stage. Specifically, the detail refinement stage, named refinement synchronization, uses the self-modality attention refinement module and the dynamic weight refinement module to accurately describe and capture approximate coordinate positions and feature information of salient objects. The feature pick-and-pass and refinement stage progressively picks and refines the prediction results in a coarse to a fine manner by combining high-level semantic information and low-level semantic information under the guidance of attention and counter-attention. In addition, the aggregation operation is used to fuse detail refinement information as well as mixture loss for supervised network training, which effectively improves the model performance from three perspectives: pixel, region, and statistics. Extensive experiments on two benchmarks datasets demonstrate that our proposed IP2GRNet, both qualitatively and quantitatively, outperforms the state-of-the-art saliency detectors.