Progressively Guided Alternate Refinement Network for RGB-D Salient Object Detection
This work addresses efficient and accurate salient object detection in complex scenarios using RGB-D data, representing an incremental improvement over existing fusion-based methods.
The paper tackles RGB-D salient object detection by proposing a progressively guided alternate refinement network that refines initial predictions using lightweight depth features and guided residual blocks, achieving state-of-the-art performance with 71 FPS and a model size of 64.9 MB.
In this paper, we aim to develop an efficient and compact deep network for RGB-D salient object detection, where the depth image provides complementary information to boost performance in complex scenarios. Starting from a coarse initial prediction by a multi-scale residual block, we propose a progressively guided alternate refinement network to refine it. Instead of using ImageNet pre-trained backbone network, we first construct a lightweight depth stream by learning from scratch, which can extract complementary features more efficiently with less redundancy. Then, different from the existing fusion based methods, RGB and depth features are fed into proposed guided residual (GR) blocks alternately to reduce their mutual degradation. By assigning progressive guidance in the stacked GR blocks within each side-output, the false detection and missing parts can be well remedied. Extensive experiments on seven benchmark datasets demonstrate that our model outperforms existing state-of-the-art approaches by a large margin, and also shows superiority in efficiency (71 FPS) and model size (64.9 MB).