R³Net: Recurrent Residual Refinement Network for Saliency Detection

R³Net: Recurrent Residual Refinement Network for Saliency Detection

Zijun Deng, Xiaowei Hu, Lei Zhu, Xuemiao Xu, Jing Qin, Guoqiang Han, Pheng-Ann Heng

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence
Main track. Pages 684-690. https://doi.org/10.24963/ijcai.2018/95

Saliency detection is a fundamental yet challenging task in computer vision, aiming at highlighting the most visually distinctive objects in an image. We propose a novel recurrent residual refinement network (R^3Net) equipped with residual refinement blocks (RRBs) to more accurately detect salient regions of an input image. Our RRBs learn the residual between the intermediate saliency prediction and the ground truth by alternatively leveraging the low-level integrated features and the high-level integrated features of a fully convolutional network (FCN). While the low-level integrated features are capable of capturing more saliency details, the high-level integrated features can reduce non-salient regions in the intermediate prediction. Furthermore, the RRBs can obtain complementary saliency information of the intermediate prediction, and add the residual into the intermediate prediction to refine the saliency maps. We evaluate the proposed R^3Net on five widely-used saliency detection benchmarks by comparing it with 16 state-of-the-art saliency detectors. Experimental results show that our network outperforms our competitors in all the benchmark datasets.
Keywords:
Machine Learning: Deep Learning
Computer Vision: Recognition: Detection, Categorization, Indexing, Matching, Retrieval, Semantic Interpretation
Computer Vision: Perception
Machine Learning Applications: Applications of Supervised Learning
Computer Vision: Computer Vision