We present an effective method to progressively integrate and refine the
cross-modality complementarities for RGB-D salient object detection (SOD). The
proposed network mainly solves two challenging issues: 1) how to effectively
integrate the complementary information from RGB image and its corresponding
depth map, and 2) how to adaptively select more saliency-related features.
First, we propose a cross-modality feature modulation (cmFM) module to enhance
feature representations by taking the depth features as prior, which models the
complementary relations of RGB-D data. Second, we propose an adaptive feature
selection (AFS) module to select saliency-related features and suppress the
inferior ones. The AFS module exploits multi-modality spatial feature fusion
with the self-modality and cross-modality interdependencies of channel features
are considered. Third, we employ a saliency-guided position-edge attention
(sg-PEA) module to encourage our network to focus more on saliency-related
regions. The above modules as a whole, called cmMS block, facilitates the
refinement of saliency features in a coarse-to-fine fashion. Coupled with a
bottom-up inference, the refined saliency features enable accurate and
edge-preserving SOD. Extensive experiments demonstrate that our network
outperforms state-of-the-art saliency detectors on six popular RGB-D SOD
benchmarks.

本文提出了一个名为 cmMS block 的模块，结合了 cross-modality feature modulation、adaptive feature selection 和 saliency-guided position-edge attention，可以逐步整合和完善 RGB-D 显著性检测中的交叉模态补充关系，有效提高了精度表现。