Abstract Recent progress on salient object detection is benefifi- cial from Fully Convolutional Neural Network (FCN). The saliency cues contained in multi-level convolutional features are complementary for detecting salient objects. How to integrate multi-level features becomes an open problem in saliency detection. In this paper, we propose a novel bi-directional message passing model to integrate multilevel features for salient object detection. At fifirst, we adopt a Multi-scale Context-aware Feature Extraction Module (MCFEM) for multi-level feature maps to capture rich context information. Then a bi-directional structure is designed to pass messages between multi-level features, and a gate function is exploited to control the message passing rate. We use the features after message passing, which simultaneously encode semantic information and spatial details, to predict saliency maps. Finally, the predicted results are effificiently combined to generate the fifinal saliency map. Quantitative and qualitative experiments on fifive benchmark datasets demonstrate that our proposed model performs favorably against the state-of-the-art methods under different evaluation metrics.