Centralized Information Interaction for Salient Object Detection
This work provides an incremental improvement for researchers and practitioners working on salient object detection by offering a more effective feature aggregation method.
This paper addresses the limitation of U-shape structures in salient object detection by proposing a centralized information interaction strategy that connects bottom-up and top-down pathways. This approach achieves superior performance against state-of-the-art methods on five benchmarks with reduced computational complexity.
The U-shape structure has shown its advantage in salient object detection for efficiently combining multi-scale features. However, most existing U-shape based methods focused on improving the bottom-up and top-down pathways while ignoring the connections between them. This paper shows that by centralizing these connections, we can achieve the cross-scale information interaction among them, hence obtaining semantically stronger and positionally more precise features. To inspire the potential of the newly proposed strategy, we further design a relative global calibration module that can simultaneously process multi-scale inputs without spatial interpolation. Benefiting from the above strategy and module, our proposed approach can aggregate features more effectively while introducing only a few additional parameters. Our approach can cooperate with various existing U-shape-based salient object detection methods by substituting the connections between the bottom-up and top-down pathways. Experimental results demonstrate that our proposed approach performs favorably against the previous state-of-the-arts on five widely used benchmarks with less computational complexity. The source code will be publicly available.