U2-Net: Going deeper with nested U-structure for salient object detection

• Published in: Pattern recognition Vol. 106; p. 107404
• Main Authors: Qin, Xuebin, Zhang, Zichen, Huang, Chenyang, Dehghan, Masood, Zaiane, Osmar R., Jagersand, Martin
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.10.2020
• Subjects: Convolutional neural network; Multi-scale feature extraction; Nested U-structure; Network architecture design; Salient object detection; Nested U-structure; Network architecture design; Salient object detection; Convolutional neural network; Multi-scale feature extraction

•A novel ReSidual U-block (RSU) is designed to capture multi-scale deep features.•A nested U-structure, called U2-Net, that uses RSU is developed for salient object detection.•Both large (176.3 MB) and small (4.7 MB) instances of U2-Net get competitive results. In this paper, we design a simple yet...