DCMNet: Discriminant and cross-modality network for RGB-D salient object detection. (15th March 2023)

• Record Type: Journal Article
• Authors: Wang, Fasheng; Wang, Ruimin; Sun, Fuming
• Is Part Of: Expert systems with applications. Volume 214(2023)
• Publication Date: 2023-03-15
• Subjects: Salient object detection -- Depth map -- Depth decomposition and recomposition module -- Multi-cross attention module; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2022.119047
• Languages: English
• ISSNs: 0957-4174

Abstract

Abstract: It is well-acknowledged that depth maps contain affluent spatial information which is crucial to explicitly distinguish the foreground and background in Salient Object Detection (SOD). With the help of depth maps, the performance has been pushed to the peak in SOD. Nevertheless, some depth maps with low quality are not potent for capturing accurate spatial information. Hence, it is not desirable to utilize depth maps indiscriminately. To this end, we propose a Discriminant and Cross-Modality Network (DCMNet) for RGB-D salient object detection. In DCMNet, we integrate a module named Depth Decomposition and Recomposition Module (DDRM) to filter depth maps with low quality. Thereafter, we conduct a quality enhancement procedure towards these detrimental depth maps. Meanwhile, we propose a Multi-Cross Attention Module (MCAM), which combines spatial attention with channel attention in a multi-cross way for better exploiting rich details about the salient object from RGB-stream and depth-stream. In addition, we employ Res2Net model to efficiently excavate foreground information and it is named as Image Pretraining Model (IPM). By embedding DDRM, MCAM and IPM, the accuracy has increased by a large margin. Extensive experiments manifest our proposed approach (DCMNet) outperforms the other 14 state-of-the-art methods on five challenging public datasets. Highlights: We propose Depth Decomposition and Recomposition Module for depth restoration. We propose Multi-Cross Attention Module for better exploiting attention mechanism. The MCAM exploits multiple features to better locate salient object. We adopt Res2Net as backbone to extract more detailed features.