ReDWeb-S is a large-scale dataset for salient object detection. The dataset contains 3,179 images covering various real-world scenes and high-quality depth maps. The dataset is divided into a training set containing 2,179 RGB-D image pairs and a test set containing the remaining 1,000 image pairs.

Citation

@article{liu2021learning, title={Learning Selective Mutual Attention and Contrast for RGB-D Saliency Detection}, author={Liu, Nian and Zhang, Ni and Shao, Ling and Han, Junwei}, journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, year={2021} }