论文标题
u $^2 $ -NET：使用嵌套的U型结构更深入，以进行显着对象检测
U$^2$-Net: Going Deeper with Nested U-Structure for Salient Object Detection
论文作者
论文摘要
在本文中，我们设计了一个简单而强大的深层网络体系结构，u $^2 $ -NET，用于显着对象检测（SOD）。我们U $^2 $ -NET的架构是两级嵌套U结构。该设计具有以下优点：（1）由于我们提出的剩余u块（RSU）中不同尺寸的接收场的混合，它能够从不同尺度捕获更多的上下文信息，（2）由于在这些RSU块中使用的池化操作而没有大大增加整个体系结构的深度，而不会大大增加计算成本。该体系结构使我们能够在不使用图像分类任务中的骨架的情况下从头开始训练一个深层网络。我们实例化了拟议体系结构的两种型号，即U $^2 $ -NET（176.3 MB，GTX 1080TI GPU上的30 fps）和U $^2 $ -NET $ -NET $^{\ DAGGE} $（4.7 MB，40 fps），以促进不同环境中的用法。两种模型都在六个SOD数据集上实现竞争性能。代码可用：https：//github.com/nathanua/u-2-net。
In this paper, we design a simple yet powerful deep network architecture, U$^2$-Net, for salient object detection (SOD). The architecture of our U$^2$-Net is a two-level nested U-structure. The design has the following advantages: (1) it is able to capture more contextual information from different scales thanks to the mixture of receptive fields of different sizes in our proposed ReSidual U-blocks (RSU), (2) it increases the depth of the whole architecture without significantly increasing the computational cost because of the pooling operations used in these RSU blocks. This architecture enables us to train a deep network from scratch without using backbones from image classification tasks. We instantiate two models of the proposed architecture, U$^2$-Net (176.3 MB, 30 FPS on GTX 1080Ti GPU) and U$^2$-Net$^{\dagger}$ (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.
