Deep RGB-D Saliency Detection with Depth-Sensitive Attention and Automatic Multi-Modal Fusion

Abstract

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.

Accepted by CVPR2021, Oral

References in corpus (7)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Neural Architecture Search with Reinforcement Learning
• Structure-measure: A New Way to Evaluate Foreground Maps
• A Single Stream Network for Robust and Real-time RGB-D Salient Object Detection
• Accurate RGB-D Salient Object Detection via Collaborative Learning
• Learning RGB-D Salient Object Detection using background enclosure, depth contrast, and top-down features
• Cross-Modal Weighting Network for RGB-D Salient Object Detection