Semantic Scholar Open Access 2020 2083 sitasi

U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection

Xuebin Qin Zichen Zhang Chenyang Huang Masood Dehghan Osmar R Zaiane +1 lainnya

Lihat Sumber DOI

Abstrak

Abstract In this paper, we design a simple yet powerful deep network architecture, U2-Net, for salient object detection (SOD). The architecture of our U2-Net is a two-level nested U-structure. The design has the following advantages: (1) it is able to capture more contextual information from different scales thanks to the mixture of receptive fields of different sizes in our proposed ReSidual U-blocks (RSU), (2) it increases the depth of the whole architecture without significantly increasing the computational cost because of the pooling operations used in these RSU blocks. This architecture enables us to train a deep network from scratch without using backbones from image classification tasks. We instantiate two models of the proposed architecture, U2-Net (176.3 MB, 30 FPS on GTX 1080Ti GPU) and U2-Net† (4.7 MB, 40 FPS), to facilitate the usage in different environments. Both models achieve competitive performance on six SOD datasets. The code is available: https://github.com/NathanUA/U-2-Net .

Topik & Kata Kunci

Computer Science

Penulis (6)

Xuebin Qin

Zichen Zhang

Chenyang Huang

Masood Dehghan

Osmar R Zaiane

Martin Jägersand

Format Sitasi

APA MLA BibTeX

Qin, X., Zhang, Z., Huang, C., Dehghan, M., Zaiane, O.R., Jägersand, M. (2020). U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection. https://doi.org/10.1016/j.patcog.2020.107404

Akses Cepat

Lihat di Sumber doi.org/10.1016/j.patcog.2020.107404

Informasi Jurnal

Tahun Terbit: 2020
Bahasa: en
Total Sitasi: 2083×
Sumber Database: Semantic Scholar
DOI: 10.1016/j.patcog.2020.107404
Akses: Open Access ✓