logo
科言猫学术研究的AI总结
language
手机端手机端
  • Phone Feature微信小程序
简体中文简体中文
notice消息通知
博客博客
delete
arrow
返回

Multi-scale prototype convolutional network for few-shot semantic segmentation

delete2025-04-15
delete0
delete
OA
AI
X
Xu Ding
S
Shun Yu
J
Jingxuan Zhou
F
Fusen Guo
L
Lin Li
DOI：10.1371/journal.pone.0319905delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
少样本语义分割旨在从有限的标注数据中精确分割对象，该任务因类内变化和原型表示挑战而复杂化。为解决这些问题，我们提出了多尺度原型卷积网络（MPCN）。我们的方法引入了先验掩码生成（PMG）模块，该模块采用不同尺寸的动态核以捕获多尺度对象特征。这增强了支撑集与查询集特征之间的交互，从而提高分割精度。此外，我们提出了多尺度原型提取（MPE）模块，以克服MAP（平均平均精度）的局限性。通过增强支撑集特征、评估空间重要性以及利用多尺度下采样，我们获得了更精确的原型集合。在PASCAL-5i和COCO-20i数据集上进行的广泛实验表明，我们的方法在1-shot和5-shot设置下均取得了更优的性能。

期刊

PLoS One 封面图
PLoS One
IF:
2.6
论文数:
2.6W
被引数:
81.6W

机构

暂无机构信息
引用论文

引用论文

Adaptive Prototype Learning and Allocation for Few-Shot Segmentation用于少镜头分割的自适应原型学习和分配
err2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
IF0
err2021-06-01
err0
errOAAI
errGen Li; Varun Jampani; Laura Sevilla-Lara; Deqing Sun; Jonghyun Kim; Joongkyu Kim
err分享
err收藏
Self-Guided and Cross-Guided Learning for Few-Shot Segmentation
err2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
IF0
err2021-06-01
err0
errOAAI
errBingfeng Zhang; Jimin Xiao; Terry Qin
err分享
err收藏
PANet: Few-Shot Image Semantic Segmentation With Prototype AlignmentPANet: 具有原型对齐的少镜头图像语义分割
err2019 IEEE/CVF International Conference on Computer Vision (ICCV)
IF0
err2019-10-01
err0
errOAAI
errKaixin Wang; Jun Hao Liew; Yingtian Zou; Daquan Zhou; Jiashi Feng
err分享
err收藏
Hypercorrelation Squeeze for Few-Shot Segmenation用于少镜头分割的超相关挤压
err2021 IEEE/CVF International Conference on Computer Vision (ICCV)
IF0
err2021-10-01
err0
PREAI
errJuhong Min; Dahyun Kang; Minsu Cho
err分享
err收藏
CBAM: Convolutional Block Attention ModuleCBAM: 卷积块注意力模块
errLecture Notes in Computer Science
IF0
err2018-10-06
err0
PREAI
errSanghyun Woo; Jongchan Park; Joon-Young Lee; In So Kweon
err分享
err收藏
Decoupling Zero-Shot Semantic Segmentation
err2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
IF0
err2022-06-01
err0
errOAAI
errJian Ding; Nan Xue; Gui-Song Xia; Dengxin Dai
err分享
err收藏
Masked Cross-image Encoding for Few-shot Segmentation
err2023 IEEE International Conference on Multimedia and Expo (ICME)
IF0
err2023-07-01
err0
errOAAI
errWenbo Xu; Huaxi Huang; Ming Cheng; Litao Yu; Qiang Wu; Jian Zhang
err分享
err收藏
Non-local Neural Networks非局部神经网络
err2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
IF0
err2018-06-01
err0
errOAAI
errXiaolong Wang; Ross Girshick; Abhinav Gupta; Kaiming He
err分享
err收藏
A review of semantic segmentation using deep neural networks基于深度神经网络的语义分割研究综述
errINTERNATIONAL JOURNAL OF MULTIMEDIA INFORMATION RETRIEVAL
IF2.9
err2017-11-24
err530
errOAAI
errGuo, Yanming; Liu, Yu; Georgiou, Theodoros; Lew, Michael S.
err分享
err收藏
Squeeze-and-Excitation Networks挤压和激励网络
err2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
IF0
err2018-06-01
err0
errOAAI
errJie Hu; Li Shen; Gang Sun
err分享
err收藏
学者 查看更多内容