LAUSR

Salient object detection (SOD) is a binary pixelwise classification to distinguish objects in an image and also has attracted many research interests in the optical remote sensing images (RSIs). The existing state-of-the-art method exploits the full encoder–decoder architecture to predict salient objects in the optical RSIs, suffering from the problem of unsmooth edges and incomplete structures. To address these problems, in this article, we propose a boundary-aware network (BANet) with two-stage partial decoders sharing the same encoders for SOD in RSIs. Specifically, a boundary-aware partial decoder (BAD) is introduced at the first stage to focus on learning clear edges of salient objects. To solve the pixel-imbalance problem between boundary and background, an edge-aware loss is proposed to guide learning the BAD network. The resulting features are then used in turn to enhance high-level features. Afterward, the structure-aware partial decoder (SAD) is further introduced at the second stage to improve the structure integrity of salient objects. To alleviate the problem of incomplete structures, the structural-similarity loss is further proposed to supervise learning the SAD network. In a consequence, our proposed BANet can predict salient objects with clear edges and complete structure, while reducing model parameters due to the discardment of low-level features. Besides, training a deep neural network requires a large amount of images, and the current benchmark datasets for optical RSIs are not large enough. Therefore, we also create a large-scale challenging dataset for SOD in RSIs. Extensive experiments demonstrate that our proposed BANet outperforms previous RSI SOD models on all the existing benchmark datasets and our new presented dataset available at https://github.com/QingpingZheng/RSISOD.