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

•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...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Pattern recognition Ročník 106; s. 107404
Hlavní autoři:	Qin, Xuebin, Zhang, Zichen, Huang, Chenyang, Dehghan, Masood, Zaiane, Osmar R., Jagersand, Martin
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Elsevier Ltd 01.10.2020
Témata:	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
ISSN:	0031-3203, 1873-5142
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	•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 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.
ISSN:	0031-3203 1873-5142
DOI:	10.1016/j.patcog.2020.107404