Deep RGB-D Saliency Detection with Depth-Sensitive Attention and Automatic Multi-Modal Fusion
This work addresses the problem of improving object detection accuracy in RGB-D images for computer vision applications, representing an incremental advancement with novel components.
The paper tackled RGB-D salient object detection by introducing a depth-sensitive attention module for RGB feature enhancement and an automatic architecture search for multi-modal fusion, achieving state-of-the-art results on seven benchmarks.
RGB-D salient object detection (SOD) is usually formulated as a problem of classification or regression over two modalities, i.e., RGB and depth. Hence, effective RGBD feature modeling and multi-modal feature fusion both play a vital role in RGB-D SOD. In this paper, we propose a depth-sensitive RGB feature modeling scheme using the depth-wise geometric prior of salient objects. In principle, the feature modeling scheme is carried out in a depth-sensitive attention module, which leads to the RGB feature enhancement as well as the background distraction reduction by capturing the depth geometry prior. Moreover, to perform effective multi-modal feature fusion, we further present an automatic architecture search approach for RGB-D SOD, which does well in finding out a feasible architecture from our specially designed multi-modal multi-scale search space. Extensive experiments on seven standard benchmarks demonstrate the effectiveness of the proposed approach against the state-of-the-art.