Dual Priors Network for RGB-D Salient Object Detection
Yuewang Xu, Li Zhao, Shaoli Cao, Shijie Feng · 2022 IEEE International Conference on Big Data (Big Data) · 2022
Although the detection accuracy of RGB-D salient object detection by deep learning has met most of the task requirements, it is still a challenge to predict complete salient objects under the guidance of poor depth maps. In this paper, edge prior and depth prior are utilized to guide the network to detect salient objects, and a novel dual priors network called DPNet is proposed for RGB-D SOD. DPNet utilizes edge priors to compensate for the inadequate guidance of low-quality depth maps. Specially, the input RGB and depth maps are encoded by ResNet-50 backbone. To fuse these information effectively, multi-modal feature fusion module downsamples high-resolution features to enhance low-resolution features with its rich semantic information. Then the initial salient masks are decoded by a coarse-grained mask decoder. In addition, edge prior serves as label and is captured by an edge aware module. Finally, the fine-grained salient masks are obtained by fusing the initial salient masks and the salient edges. The experimental results on six benchmarks indicate that the proposed method outperforms ten state-of-the-art methods in six evaluation metrics.