咨询与建议

限定检索结果

文献类型

  • 17 篇 期刊文献
  • 16 篇 会议

馆藏范围

  • 33 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 32 篇 工学
    • 29 篇 计算机科学与技术...
    • 14 篇 电气工程
    • 7 篇 软件工程
    • 3 篇 信息与通信工程
    • 2 篇 生物医学工程(可授...
    • 1 篇 仪器科学与技术
    • 1 篇 电子科学与技术(可...
    • 1 篇 控制科学与工程
    • 1 篇 测绘科学与技术
  • 11 篇 医学
    • 7 篇 临床医学
    • 5 篇 特种医学
  • 5 篇 理学
    • 2 篇 物理学
    • 1 篇 数学
    • 1 篇 化学
    • 1 篇 地理学
    • 1 篇 生物学

主题

  • 33 篇 weakly-supervise...
  • 6 篇 deep learning
  • 4 篇 semantic segment...
  • 3 篇 image segmentati...
  • 3 篇 training
  • 2 篇 task analysis
  • 2 篇 image-level labe...
  • 2 篇 semantics
  • 2 篇 image classifica...
  • 2 篇 single-stage
  • 2 篇 convolutional ne...
  • 2 篇 class activation...
  • 1 篇 dense regression...
  • 1 篇 covid-19
  • 1 篇 vision transform...
  • 1 篇 tools
  • 1 篇 visual words lea...
  • 1 篇 transformer
  • 1 篇 autonomous drivi...
  • 1 篇 histopathology i...

机构

  • 2 篇 sun yat sen univ...
  • 2 篇 northwest normal...
  • 2 篇 key lab cloud co...
  • 1 篇 wuhan univ liesm...
  • 1 篇 nanjing univ sch...
  • 1 篇 east china norma...
  • 1 篇 univ electro com...
  • 1 篇 ecole polytech f...
  • 1 篇 uppsala univ upp...
  • 1 篇 xiamen univ sch ...
  • 1 篇 australian natl ...
  • 1 篇 wuhan univ natl ...
  • 1 篇 guangxi normal u...
  • 1 篇 ecole polytech f...
  • 1 篇 jd explore acad ...
  • 1 篇 northwestern pol...
  • 1 篇 tsinghua univ th...
  • 1 篇 northwestern pol...
  • 1 篇 sapienza diag ro...
  • 1 篇 shanghai jiao to...

作者

  • 2 篇 yanai keiji
  • 2 篇 shimoda wataru
  • 2 篇 li xiaolong
  • 2 篇 ma huifang
  • 2 篇 wang chen
  • 2 篇 zhang di
  • 2 篇 li zhixin
  • 1 篇 saleh fatemeh sa...
  • 1 篇 bonnin-pascual f...
  • 1 篇 tian zhiqiang
  • 1 篇 li zhenshi
  • 1 篇 wang wenye
  • 1 篇 yao kai
  • 1 篇 chen junliang
  • 1 篇 ma andy j.
  • 1 篇 onozuka yuya
  • 1 篇 wang haonan
  • 1 篇 du youtian
  • 1 篇 benitez-garcia g...
  • 1 篇 she jinwen

语言

  • 33 篇 英文
检索条件"主题词=weakly-supervised semantic segmentation"
33 条 记 录,以下是1-10 订阅
排序:
Spatial Frequency-Aware Self-Distillation for weakly-supervised semantic segmentation
Spatial Frequency-Aware Self-Distillation for Weakly-Supervi...
收藏 引用
2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025
作者: Fang, Jingyuan Ning, Yang Nie, Xiushan School of Computer Science and Technology Shandong Jianzhu University Jinan China
weakly-supervised semantic segmentation (WSSS) aims to achieve pixel-level classification under image-level supervision. Recent class activation map (CAM)-based methods seek to expand foreground activation while suppr... 详细信息
来源: 评论
Enhancing weakly supervised semantic segmentation with efficient and robust neighbor-attentive superpixel aggregation
收藏 引用
IMAGE AND VISION COMPUTING 2025年 154卷
作者: Wang, Chen Ma, Huifang Zhang, Di Li, Xiaolong Li, Zhixin Northwest Normal Univ Coll Comp Sci & Engn Lanzhou 730070 Gansu Peoples R China Guangxi Normal Univ Key Lab Educ Blockchain & Intelligent Technol Minist Educ Guilin 541004 Guangxi Peoples R China Key Lab Cloud Comp Gansu Prov Lanzhou 730070 Gansu Peoples R China
Image-level weakly-supervised semantic segmentation (WSSS) has become prominent as a technique that utilizes readily available image-level supervisory information. However, traditional methods that rely on pseudo-segm... 详细信息
来源: 评论
weakly-supervised semantic segmentation with Visual Words Learning and Hybrid Pooling
收藏 引用
INTERNATIONAL JOURNAL OF COMPUTER VISION 2022年 第4期130卷 1127-1144页
作者: Ru, Lixiang Du, Bo Zhan, Yibing Wu, Chen Wuhan Univ Natl Engn Res Ctr Multimedia Software Inst Artificial Intelligence Sch Comp Sci Wuhan Peoples R China Wuhan Univ Hubei Key Lab Multimedia & Network Commun Engn Wuhan Peoples R China JD Explore Acad JDcom Beijing Peoples R China Wuhan Univ LIESMARS Wuhan Peoples R China
weakly-supervised semantic segmentation (WSSS) methods with image-level labels generally train a classification network to generate the Class Activation Maps (CAMs) as the initial coarse segmentation labels. However, ... 详细信息
来源: 评论
weakly-supervised semantic segmentation via Label Re-assignment in Dual-View Framework  33rd
Weakly-Supervised Semantic Segmentation via Label Re-assignm...
收藏 引用
33rd International Conference on Artificial Neural Networks and Machine Learning (ICANN)
作者: Wang, Chen Zhang, Di Li, Xiaolong Ma, Huifang Li, Zhixin Northwest Normal Univ Coll Comp Sci & Engn Lanzhou Peoples R China Key Lab Cloud Comp Gansu Prov Lanzhou Peoples R China Guangxi Normal Univ Key Lab Educ Blockchain & Intelligent Technol Minist Educ Guilin Peoples R China
Mining accurate Class Activation Maps (CAMs) is essential for weakly-supervised semantic segmentation (WSSS). However, the CAMs only activate the most discriminative semantic regions, which can severely affect the seg... 详细信息
来源: 评论
Adversarial Learning of Object-Aware Activation Map for weakly-supervised semantic segmentation
收藏 引用
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2023年 第8期33卷 3935-3946页
作者: Chen, Junliang Lu, Weizeng Li, Yuexiang Shen, Linlin Duan, Jinming Shenzhen Univ Comp Vis Inst Sch Comp Sci & Software Engn Shenzhen 518060 Peoples R China Shenzhen Univ Shenzhen Inst Artificial Intelligence & Robot Soc Guangdong Key Lab Intelligent Informat Proc Shenzhen 518060 Peoples R China Tencent Jarvis Lab Shenzhen 518057 Peoples R China Univ Birmingham Sch Comp Sci Birmingham B15 2TT England
Recent years have witnessed impressive advances in the area of weakly-supervised semantic segmentation (WSSS). However, most of existing approaches are based on class activation maps (CAMs), which suffer from the unde... 详细信息
来源: 评论
Incorporating Network Built-in Priors in weakly-supervised semantic segmentation
收藏 引用
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2018年 第6期40卷 1382-1396页
作者: Saleh, Fatemeh Sadat Aliakbarian, Mohammad Sadegh Salzmann, Mathieu Petersson, Lars Alvarez, Jose M. Gould, Stephen Australian Natl Univ Coll Engn & Comp Sci GPO Box 4 Canberra ACT 0200 Australia CSIRO Data61 Canberra ACT 0200 Australia Ecole Polytech Fed Lausanne CVLab CH-1015 Lausanne Switzerland
Pixel-level annotations are expensive and time consuming to obtain. Hence, weak supervision using only image tags could have a significant impact in semantic segmentation. Recently, CNN-based methods have proposed to ... 详细信息
来源: 评论
Co-attention dictionary network for weakly-supervised semantic segmentation
收藏 引用
NEUROCOMPUTING 2022年 第0期486卷 272-285页
作者: Wan, Weitao Chen, Jiansheng Yang, Ming-Hsuan Ma, Huimin Tsinghua Univ Dept Elect Engn Beijing 100084 Peoples R China Univ Calif Merced Merced CA USA Tsinghua Univ Beijing Natl Res Ctr Informat Sci & Technol Beijing 100084 Peoples R China Univ Sci & Technol Beijing Sch Comp & Commun Engn Beijing 100083 Peoples R China
In this paper, we propose the co-attention dictionary network (CODNet) for weakly-supervised semantic segmentation using only image-level class labels. The CODNet model exploits extra semantic information by jointly l... 详细信息
来源: 评论
A weakly-supervised semantic segmentation Approach Based on the Centroid Loss: Application to Quality Control and Inspection
收藏 引用
IEEE ACCESS 2021年 9卷 69010-69026页
作者: Yao, Kai Ortiz, Alberto Bonnin-Pascual, Francisco Univ Balearic Isl Dept Math & Comp Sci Palma De Mallorca 07122 Spain Inst Invest Sanitaria Illes Balears IDISBA Palma De Mallorca 07120 Spain
It is generally accepted that one of the critical parts of current vision algorithms based on deep learning and convolutional neural networks is the annotation of a sufficient number of images to achieve competitive p... 详细信息
来源: 评论
Partial Image Texture Translation Using weakly-supervised semantic segmentation  11th
Partial Image Texture Translation Using Weakly-Supervised Se...
收藏 引用
11th JSAI International Symposium on Artificial Intelligence (JSAI-ISAI) / 13th International Workshop on Juris-Informatics (JURISIN)
作者: Benitez-Garcia, Gibran Shimoda, Wataru Matsuo, Shin Yanai, Keiji Univ Electrocommun Dept Informat 1-5-1 Chofugaoka Chofu Tokyo 1828585 Japan
The field of Neural Style Transfer (NST) has led to interesting applications that enables to transform the reality as human beings perceive. Particularly, NST for material translation aims to change the material (text... 详细信息
来源: 评论
IMAGE AUGMENTATION WITH CONTROLLED DIFFUSION FOR weakly-supervised semantic segmentation  49
IMAGE AUGMENTATION WITH CONTROLLED DIFFUSION FOR WEAKLY-SUPE...
收藏 引用
49th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
作者: Wu, Wangyu Dai, Tianhong Huang, Xiaowei Ma, Fei Xiao, Jimin Univ Liverpool Xian Jiaotong Liverpool Merseyside England Univ Liverpool Liverpool Merseyside England Univ Aberdeen Aberdeen Scotland
weakly-supervised semantic segmentation (WSSS), which aims to train segmentation models solely using image-level labels, has achieved significant attention. Existing methods primarily focus on generating high-quality ... 详细信息
来源: 评论