A Unified Structure for Efficient RGB and RGB-D Salient Object Detection
This work provides a more efficient and unified approach to salient object detection for researchers and practitioners working with both RGB and RGB-D data, which traditionally required separate models.
This paper proposes a unified structure for salient object detection (SOD) that efficiently handles both RGB and RGB-D images. The method achieves state-of-the-art performance on various datasets for both RGB and RGB-D SOD tasks across most metrics.
Salient object detection (SOD) has been well studied in recent years, especially using deep neural networks. However, SOD with RGB and RGB-D images is usually treated as two different tasks with different network structures that need to be designed specifically. In this paper, we proposed a unified and efficient structure with a cross-attention context extraction (CRACE) module to address both tasks of SOD efficiently. The proposed CRACE module receives and appropriately fuses two (for RGB SOD) or three (for RGB-D SOD) inputs. The simple unified feature pyramid network (FPN)-like structure with CRACE modules conveys and refines the results under the multi-level supervisions of saliency and boundaries. The proposed structure is simple yet effective; the rich context information of RGB and depth can be appropriately extracted and fused by the proposed structure efficiently. Experimental results show that our method outperforms other state-of-the-art methods in both RGB and RGB-D SOD tasks on various datasets and in terms of most metrics.