已入深夜,您辛苦了!由于当前在线用户较少,发布求助请尽量完整的填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!祝你早点完成任务,早点休息,好梦!

UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation

计算机科学 分割 人工智能 模式识别(心理学) 特征(语言学) 编码器 卷积神经网络 加速 图像分割 推论 计算机视觉 语言学 操作系统 哲学
作者
Zongwei Zhou,Md Mahfuzur Rahman Siddiquee,Nima Tajbakhsh,Jianming Liang
出处
期刊:IEEE Transactions on Medical Imaging [Institute of Electrical and Electronics Engineers]
卷期号:39 (6): 1856-1867 被引量:2542
标识
DOI:10.1109/tmi.2019.2959609
摘要

The state-of-the-art models for medical image segmentation are variants of U-Net and fully convolutional networks (FCN). Despite their success, these models have two limitations: (1) their optimal depth is apriori unknown, requiring extensive architecture search or inefficient ensemble of models of varying depths; and (2) their skip connections impose an unnecessarily restrictive fusion scheme, forcing aggregation only at the same-scale feature maps of the encoder and decoder sub-networks. To overcome these two limitations, we propose UNet++, a new neural architecture for semantic and instance segmentation, by (1) alleviating the unknown network depth with an efficient ensemble of U-Nets of varying depths, which partially share an encoder and co-learn simultaneously using deep supervision; (2) redesigning skip connections to aggregate features of varying semantic scales at the decoder sub-networks, leading to a highly flexible feature fusion scheme; and (3) devising a pruning scheme to accelerate the inference speed of UNet++. We have evaluated UNet++ using six different medical image segmentation datasets, covering multiple imaging modalities such as computed tomography (CT), magnetic resonance imaging (MRI), and electron microscopy (EM), and demonstrating that (1) UNet++ consistently outperforms the baseline models for the task of semantic segmentation across different datasets and backbone architectures; (2) UNet++ enhances segmentation quality of varying-size objects-an improvement over the fixed-depth U-Net; (3) Mask RCNN++ (Mask R-CNN with UNet++ design) outperforms the original Mask R-CNN for the task of instance segmentation; and (4) pruned UNet++ models achieve significant speedup while showing only modest performance degradation. Our implementation and pre-trained models are available at https://github.com/MrGiovanni/UNetPlusPlus.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
1秒前
ding应助wangting采纳,获得10
1秒前
111完成签到,获得积分10
2秒前
王线性完成签到,获得积分10
4秒前
科研通AI2S应助rose采纳,获得10
4秒前
fsznc1完成签到 ,获得积分0
5秒前
8秒前
10秒前
乐观夜蕾完成签到,获得积分10
10秒前
张佳明完成签到,获得积分10
11秒前
流体离子发电机完成签到,获得积分10
11秒前
Lucas应助洁净寒凝采纳,获得10
11秒前
木石前盟发布了新的文献求助10
15秒前
15秒前
16秒前
17秒前
17秒前
17秒前
17秒前
Chain发布了新的文献求助10
20秒前
nickthename发布了新的文献求助10
20秒前
CQ发布了新的文献求助10
21秒前
21秒前
简单又槐发布了新的文献求助30
22秒前
wuludie应助悬壶济世之骨科采纳,获得10
24秒前
CQ完成签到,获得积分10
26秒前
26秒前
Ava应助violet3zz采纳,获得10
28秒前
FashionBoy应助许思真采纳,获得10
28秒前
wang完成签到,获得积分20
29秒前
chydlbb完成签到,获得积分10
29秒前
领导范儿应助HDD采纳,获得10
29秒前
可爱的函函应助Chain采纳,获得30
30秒前
开朗板栗发布了新的文献求助10
31秒前
正直的以冬完成签到,获得积分10
32秒前
情怀应助pp-doctor采纳,获得10
33秒前
33秒前
随遇而安应助简单又槐采纳,获得10
34秒前
开朗板栗完成签到,获得积分20
38秒前
chydlbb发布了新的文献求助10
38秒前
高分求助中
The late Devonian Standard Conodont Zonation 2000
Nickel superalloy market size, share, growth, trends, and forecast 2023-2030 2000
The Lali Section: An Excellent Reference Section for Upper - Devonian in South China 1500
Smart but Scattered: The Revolutionary Executive Skills Approach to Helping Kids Reach Their Potential (第二版) 1000
Very-high-order BVD Schemes Using β-variable THINC Method 830
Mantiden: Faszinierende Lauerjäger Faszinierende Lauerjäger 800
PraxisRatgeber: Mantiden: Faszinierende Lauerjäger 800
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3248529
求助须知:如何正确求助?哪些是违规求助? 2891960
关于积分的说明 8269265
捐赠科研通 2559983
什么是DOI,文献DOI怎么找? 1388824
科研通“疑难数据库(出版商)”最低求助积分说明 650913
邀请新用户注册赠送积分活动 627798