Global-aware Interaction Network for RGB-D salient object detection
Zijian Jiang, Ling Hong Yu, Han Yu, Junru Li, Fanglin Niu · Neurocomputing · 2024
Most existing RGB-D salient object detection (SOD) methods rely on depth images to complement RGB images , improving detection accuracy. However, under complex or low-light conditions, the poor quality of depth images often introduces substantial interference, negatively affecting model performance. Consequently, effectively integrating complementary information from both RGB and depth images remains a significant challenge in this field. In this paper, we propose a Global-aware Interaction Network (GAINet) for RGB-D SOD to better capture depth image cues and address modality discrepancies. Specifically, we introduce a Cross-Modal Feature Fusion Module (CMFFM), which consists of a Feature Extraction Enhancement (FEE) module and a Modal Interaction (MI) module. The FEE module refines and enhances the features from both RGB and depth images, while the MI module uses depth features to guide the detection of salient objects in the RGB features. Additionally, a Multi-layer Complementary Module (MCM) is designed to further enhance and refine multi-level complementary features, enabling step-by-step decoding of salient feature maps. A hybrid loss function is employed to optimize GAINet’s training process. Extensive experiments show that GAINet outperforms 15 state-of-the-art RGB-D SOD methods across six publicly available datasets. The codes can be found in https://github.com/wzxxmj/GAINet/ .