Adaptive fusion network for RGB-D salient object detection

Existing state-of-the-art RGB-D saliency detection models mainly utilize the depth information as com-plementary cues to enhance the RGB information. However, depth maps can be easily influenced by envi-ronment and hence are full of noises. Thus, indiscriminately integrating multi-modality (i.e., RGB and depth) features may induce noise-degraded saliency maps. In this paper, we propose a novel Adaptive Fusion Network (AFNet) to solve this problem. Specifically, we design a triplet encoder network consist-ing of three subnetworks to process RGB, depth, and fused features, respectively. The three subnetworks are interlinked and form a grid net to facilitate mutual refinement of these multi-modality features. Moreover, we propose a Multi-modality Feature Interaction (MFI) module to exploit complementary cues between depth and RGB modalities and adaptively fuse the multi-modality features. Finally, we design the Cascaded Feature Interweaved Decoder (CFID) to exploit complementary information between multi-level features and refine them iteratively to achieve accurate saliency detection. Experimental results on six commonly used benchmark datasets verify that the proposed AFNet outperforms 20 state-of-the-art counterparts in terms of six widely adopted evaluation metrics. Source code will be pub-licly available athttps://github.com/clelouch/AFNet upon paper acceptance. (c) 2022 Elsevier B.V. All rights reserved.