Multi-Scale Iterative Refinement Network for RGB-D Salient Object Detection

Abstract

The extensive research leveraging RGB-D information has been exploited in salient object detection. However, salient visual cues appear in various scales and resolutions of RGB images due to semantic gaps at different feature levels. Meanwhile, similar salient patterns are available in cross-modal depth images as well as multi-scale versions. Cross-modal fusion and multi-scale refinement are still an open problem in RGB-D salient object detection task. In this paper, we begin by introducing top-down and bottom-up iterative refinement architecture to leverage multi-scale features, and then devise attention based fusion module (ABF) to address on cross-modal correlation. We conduct extensive experiments on seven public datasets. The experimental results show the effectiveness of our devised method

arXiv comment40 pages

References in corpus (8)

• Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation
• ParseNet: Looking Wider to See Better
• Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks
• Visual Saliency Detection Based on Multiscale Deep CNN Features
• RGBD Salient Object Detection via Deep Fusion
• Three Birds One Stone: A General Architecture for Salient Object Segmentation, Edge Detection and Skeleton Extraction
• Deep RGB-D Saliency Detection with Depth-Sensitive Attention and Automatic Multi-Modal Fusion
• Adaptive Fusion for RGB-D Salient Object Detection