11 March 2024 in IEEE Transactions on Geoscience and Remote Sensing
Current state-of-the-art methods for salient object detection in optical remote sensing images (RSI-SOD) primarily relies on individual image context to detect salient objects. However, the potential of cross-image contexts remains largely unexplored in existing works, which can provide valuable auxiliary and complementary information for discriminating object representations in RSIs. In this paper, we investigate the utilization of cross-image contextual information for RSI-SOD. We propose a novel memory-based context propagation network (MCP-Net) to harness dataset-level contextual information. MCP-Net incorporates a cross-image dual memory module (CDM) to store dataset-level information and utilize it to generate contextual information for the current image. CDM effectively captures intra-scene variations by leveraging both foreground and background memory banks, resulting in improved object representations. Additionally, we enhance the representations by leveraging scale-aware context information within individual images. To preserve RSI details before memory modules, we introduce a shared attention-guided fusion module (SAF) to align the adjacent network-level features. Extensive evaluation results demonstrate the superior performance of our proposed method compared to state-of-the-art methods on three public benchmarks. These results affirm that the inclusion of cross-image contexts can significantly benefit salient object detection in remote sensing images.
30 October 2024 in IEEE Geoscience and Remote Sensing Letters
Thoroughly utilizing scale-aware context features to accurately segment entire salient regions remains a significant challenge in salient object detection (SOD) for optical remote sensing images (RSIs). In this letter, we propose a novel dynamic context coordination network (DCC-Net), which is capable of highlighting complete salient regions by exploiting feature coordination across different network levels. DCC-Net is composed of three components: a feature encoder, a bilinear purification (BP) module, and a dynamic context coordination (DCC) module. First, we adopt a standard feature encoder to extract multiscale features. Second, a BP module is proposed to establish a global correlation between horizontal and vertical directions and purify saliency representations. Finally, a DCC module is designed to facilitate context coordination from low to high resolutions by conditioning the convolution kernels dynamic on adjacent context. Comparison experiments are performed on the ORSSD, EORSSD, and ORSI-4199 datasets, demonstrating the superiority of our proposed method against other state-of-the-art methods and verifying the effectiveness of the DCC.