Boosting RGB-D Saliency Detection by Leveraging Unlabeled RGB Images

TL;DR

This paper introduces a semi-supervised deep learning framework that leverages unlabeled RGB images with pseudo depth maps to improve RGB-D salient object detection, reducing reliance on labeled RGB-D data.

Contribution

The novel DDCNN architecture and semi-supervised teacher-student framework effectively utilize unlabeled RGB images to enhance RGB-D saliency detection performance.

Findings

Outperforms state-of-the-art methods on benchmark datasets.

Semi-supervised approach improves detection accuracy with fewer labeled data.

Effective use of pseudo depth maps from unlabeled RGB images.

Abstract

Training deep models for RGB-D salient object detection (SOD) often requires a large number of labeled RGB-D images. However, RGB-D data is not easily acquired, which limits the development of RGB-D SOD techniques. To alleviate this issue, we present a Dual-Semi RGB-D Salient Object Detection Network (DS-Net) to leverage unlabeled RGB images for boosting RGB-D saliency detection. We first devise a depth decoupling convolutional neural network (DDCNN), which contains a depth estimation branch and a saliency detection branch. The depth estimation branch is trained with RGB-D images and then used to estimate the pseudo depth maps for all unlabeled RGB images to form the paired data. The saliency detection branch is used to fuse the RGB feature and depth feature to predict the RGB-D saliency. Then, the whole DDCNN is assigned as the backbone in a teacher-student framework for semi-supervised learning. Moreover, we also introduce a consistency loss on the intermediate attention and saliency maps for the unlabeled data, as well as a supervised depth and saliency loss for labeled data. Experimental results on seven widely-used benchmark datasets demonstrate that our DDCNN outperforms state-of-the-art methods both quantitatively and qualitatively. We also demonstrate that our semi-supervised DS-Net can further improve the performance, even when using an RGB image with the pseudo depth map.