U2Net

本文主要是介绍U2Net，希望对大家解决编程问题提供一定的参考价值，需要的开发者们随着小编来一起学习吧！

$U 2 N e t$

1.视频教程：
B站、网易云课堂、腾讯课堂
2.代码地址：
Gitee
Github
3.存储地址：
Google云
百度云：
提取码：

工程部署项目：https://github.com/danielgatis/rembg

U2Net网络：https://codechina.csdn.net/mirrors/NathanUA/U-2-Net?utm_source=csdn_github_accelerator

1.一论文导读
2.二论文精读
3.三代码实现
4.四问题思索
5.五实验参数设置
6.六额外补充

《U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection》
—待写
作者：Xuebin Qin, Zichen Zhang, Chenyang Huang,etc
单位：
发表会议及时间：Pattern Recognition 2020

Submission history

From: Xuebin Qin [view email]
[v1] Mon, 18 May 2020 18:08:26 UTC (7,173 KB)
[v2] Wed, 5 Aug 2020 04:06:04 UTC (7,173 KB)

论文：https://arxiv.org/pdf/2005.09007.pdf

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: this https URL:https://github.com/xuebinqin/U-2-Net.