Selectivity or Invariance: Boundary-aware Salient Object Detection
This work addresses a core challenge in computer vision for applications like image segmentation, though it is incremental in improving existing SOD methods.
The paper tackles the selectivity-invariance dilemma in salient object detection by proposing a boundary-aware network with successive dilation, which enhances feature selectivity at boundaries and invariance at interiors, achieving state-of-the-art performance on six datasets.
Typically, a salient object detection (SOD) model faces opposite requirements in processing object interiors and boundaries. The features of interiors should be invariant to strong appearance change so as to pop-out the salient object as a whole, while the features of boundaries should be selective to slight appearance change to distinguish salient objects and background. To address this selectivity-invariance dilemma, we propose a novel boundary-aware network with successive dilation for image-based SOD. In this network, the feature selectivity at boundaries is enhanced by incorporating a boundary localization stream, while the feature invariance at interiors is guaranteed with a complex interior perception stream. Moreover, a transition compensation stream is adopted to amend the probable failures in transitional regions between interiors and boundaries. In particular, an integrated successive dilation module is proposed to enhance the feature invariance at interiors and transitional regions. Extensive experiments on six datasets show that the proposed approach outperforms 16 state-of-the-art methods.