Salient Object Detection in Optical Remote Sensing Images Based on Hierarchical Semantic Interaction

Abstract

Existing salient object detection methods for optical remote sensing images still face certain limitations due to complex background variations, significant scale discrepancies among targets, severe background interference, and diverse topological structures. On the one hand, the feature transmission process often neglects the constraints and complementary effects of high-level features on low-level features, leading to insufficient feature interaction and weakened model representation. On the other hand, decoder architectures generally rely on simple cascaded structures, which fail to adequately exploit and utilize contextual information. To address these challenges, this study proposes a Hierarchical Semantic Interaction Module to enhance salient object detection performance in optical remote sensing scenarios. The module introduces foreground content modeling and a hierarchical semantic interaction mechanism within a multi-scale feature space, reinforcing the synergy and complementarity among features at different levels. This effectively highlights multi-scale and multi-type salient regions in complex backgrounds. Extensive experiments on multiple optical remote sensing datasets demonstrate the effectiveness of the proposed method. Specifically, on the EORSSD dataset, our full model integrating both CA and PA modules improves the max F-measure from 0.8826 to 0.9100 (↑2.74%), increases maxE from 0.9603 to 0.9727 (↑1.24%), and enhances the S-measure from 0.9026 to 0.9295 (↑2.69%) compared with the baseline. These results clearly demonstrate the effectiveness of the proposed modules and verify the robustness and strong generalization capability of our method in complex remote sensing scenarios.

Keywords: channel adaptive enhancement; hierarchical semantic interaction; multi-scale feature fusion; optical remote sensing images; position-aware attention; salient object detection.

Figure 1

HSIMNet model network structure diagram.

Figure 2

Channel Attention Mechanism diagram.

Figure 3

Position attention mechanism structure diagram.

Figure 4

Precision–Recall (PR) curves of the proposed HSIMNet and comparison methods on the ORSSD and EORSSD datasets.

Figure 5

F-measure curves of HSIMNet and other state-of-the-art methods on the ORSSD and EORSSD datasets.

Figure 6

Qualitative comparison of salient object detection results produced by HSIMNet and representative competing methods on challenging scenes from the ORSSD and EORSSD datasets.