This paper discusses the limitations of single- and two-modal salient object detection (SOD) methods and the emergence of multi-modal SOD techniques that integrate Visible, Depth, or Thermal information. However, current multi-modal methods often rely on simple fusion techniques such as addition, multiplication and concatenation, to combine the different modalities, which is ineffective for challenging scenes, such as low illumination and background messy. To address this issue, we propose a novel multi-modal feature fusion network (MFFNet) for V-D-T salient object detection, where the two key points are the triple-modal deep fusion encoder and the progressive feature enhancement decoder. The MFFNet's triple-modal deep fusion (TDF) module is designed to integrate the features of the three modalities and explore their complementarity by utilizing mutual optimization during the encoding phase. In addition, the progressive feature enhancement decoder consists of the weighted context-enhanced feature (WCF) module, region optimization (RO) module and boundary perception (BP) module to produce region-aware and contour-aware features. After that, a multi-scale fusion (MF) module is proposed to integrate these features and generate high-quality saliency maps. We conduct extensive experiments on the VDT-2048 dataset, and our results show that the proposed MFFNet outperforms 12 state-of-the-art multi-modal methods.

Salient object detection (SOD) can be applied to consumer electronic area, which can help to identify and locate objects of interest. RGB/RGB-D (depth) salient object detection has achieved great progress in recent years. However, there is a large room for improvement in exploring the complementarity of two-modal information for RGB-T (thermal) SOD. Therefore, this paper proposes a Transformer-based Cross-modal Integration Network (i.e., TCINet) to detect salient objects in RGB-T images, which can properly fuse two-modal features and interactively aggregate two-level features. Our method consists of the siamese Swin Transformer-based encoders, the cross-modal feature fusion (CFF) module, and the interaction-based feature decoding (IFD) block. Here, the CFF module is designed to fuse the complementary information of two-modal features, where the collaborative spatial attention emphasizes salient regions and suppresses background regions of the two-modal features. Furthermore, we deploy the IFD block to aggregate two-level features, including the previous-level fused feature and the current-level encoder feature, where the IFD block bridges the large semantic gap and reduces the noise. Extensive experiments are conducted on three RGB-T datasets, and the experimental results clearly demonstrate the superiority and effectiveness of our method when compared with the cutting-edge saliency methods. The results and code of our method will be available at https://github.com/lvchengtao/TCINet.

RGB-T salient object detection (SOD) has made significant progress in recent years. However, most existing works are based on heavy models, which are not applicable to mobile devices. Additionally, there is still room for improvement in the design of cross-modal feature fusion and cross-level feature fusion. To address these issues, we propose a lightweight cross-modal information mutual reinforcement network for RGB-T SOD. Our network consists of a lightweight encoder, the cross-modal information mutual reinforcement (CMIMR) module, and the semantic-information-guided fusion (SIGF) module. To reduce the computational cost and the number of parameters, we employ the lightweight module in both the encoder and decoder. Furthermore, to fuse the complementary information between two-modal features, we design the CMIMR module to enhance the two-modal features. This module effectively refines the two-modal features by absorbing previous-level semantic information and inter-modal complementary information. In addition, to fuse the cross-level feature and detect multiscale salient objects, we design the SIGF module, which effectively suppresses the background noisy information in low-level features and extracts multiscale information. We conduct extensive experiments on three RGB-T datasets, and our method achieves competitive performance compared to the other 15 state-of-the-art methods.