CIR-Net: Cross-modality Interaction and Refinement for RGB-D Salient Object Detection
This work addresses the challenge of integrating RGB and depth data for salient object detection, an incremental improvement in computer vision for applications like robotics and autonomous systems.
The paper tackled the problem of effectively capturing and utilizing cross-modality information in RGB-D salient object detection by proposing CIR-Net, a CNN model with cross-modality interaction and refinement, which outperformed state-of-the-art methods on six benchmarks.
Focusing on the issue of how to effectively capture and utilize cross-modality information in RGB-D salient object detection (SOD) task, we present a convolutional neural network (CNN) model, named CIR-Net, based on the novel cross-modality interaction and refinement. For the cross-modality interaction, 1) a progressive attention guided integration unit is proposed to sufficiently integrate RGB-D feature representations in the encoder stage, and 2) a convergence aggregation structure is proposed, which flows the RGB and depth decoding features into the corresponding RGB-D decoding streams via an importance gated fusion unit in the decoder stage. For the cross-modality refinement, we insert a refinement middleware structure between the encoder and the decoder, in which the RGB, depth, and RGB-D encoder features are further refined by successively using a self-modality attention refinement unit and a cross-modality weighting refinement unit. At last, with the gradually refined features, we predict the saliency map in the decoder stage. Extensive experiments on six popular RGB-D SOD benchmarks demonstrate that our network outperforms the state-of-the-art saliency detectors both qualitatively and quantitatively.