Boosting RGB-D Saliency Detection by Leveraging 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.

arXiv commentAccepted by IEEE TIP

References in corpus (9)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Temporal Ensembling for Semi-Supervised Learning
• ParseNet: Looking Wider to See Better
• Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks
• High-Resolution Representations for Labeling Pixels and Regions
• Review of Visual Saliency Detection with Comprehensive Information
• RGBD Salient Object Detection via Deep Fusion
• Co-saliency Detection for RGBD Images Based on Multi-constraint Feature Matching and Cross Label Propagation
• Learning to Decompose and Disentangle Representations for Video Prediction