CAGNet: Content-Aware Guidance for Salient Object Detection

•A Content-Aware Guidance Network for Salient Object Detection is introduced.•The diverse recognition abilities of multi-level features are exploited to guide the features.•Powerful multi-scale features are extracted by enabling densely connections within large regions in the feature maps.•Our designed loss function outperforms the widely-used Cross-entropy loss by a large margin.•Our method achieves the state-of-the-art performance on five challenging datasets.