Research of Self-Attention in Image Segmentation

被引：1

作者：

Cao, Fude ^{[1
]}

Zheng, Chunguang ^{[1
]}

Huang, Limin ^{[1
]}

Wang, Aihua ^{[1
]}

Zhang, Jiong ^{[1
]}

Zhou, Feng ^{[1
]}

Ju, Haoxue ^{[1
]}

Guo, Haitao ^{[1
]}

Du, Yuxia ^{[1
]}

机构：

[1] Shandong Inst Commerce & Technol, Jinan, Shandong, Peoples R China

来源：

JOURNAL OF INFORMATION TECHNOLOGY RESEARCH | 2022年 / 15卷 / 01期

关键词：

Convolutional Neural Networks; Image Segmentation; Self-Attention;

D O I：

10.4018/JITR.298619

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

Although the traditional convolutional neural network is applied to image segmentation successfully, it has some limitations. That's the context information of the long-range on the image is not well captured. With the success of the introduction of self-attentional mechanisms in the field of natural language processing (NLP), people have tried to introduce the attention mechanism in the field of computer vision. It turns out that self-attention can really solve this long-range dependency problem. This paper is a summary on the application of self-attention to image segmentation in the past two years.

引用

页数：12

共 50 条

[21] Fusing RGB and depth with Self-attention for Unseen Object Segmentation
Lee, Joosoon
Back, Seunghyeok
Kim, Taewon
Shin, Sungho
Noh, Sangjun
Kang, Raeyoung
Kim, Jongwon
Lee, Kyoobin
2021 21ST INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION AND SYSTEMS (ICCAS 2021), 2021, : 1599 - 1605
[22] A Dual Self-Attention based Network for Image Captioning
Li, ZhiYong
Yang, JinFu
Li, YaPing
PROCEEDINGS OF THE 33RD CHINESE CONTROL AND DECISION CONFERENCE (CCDC 2021), 2021, : 1590 - 1595
[23] Background-lead self-attention for image harmonization
Lu, Min
Zhang, LingTao
Liu, YongMin
JOURNAL OF ELECTRONIC IMAGING, 2022, 31 (06)
[24] PMFSNet: Polarized multi-scale feature self-attention network for lightweight medical image segmentation
Zhong, Jiahui
Tian, Wenhong
Xie, Yuanlun
Liu, Zhijia
Ou, Jie
Tian, Taoran
Zhang, Lei
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2025, 261
[25] SwinT-Unet: Ultrasound Image Segmentation Based on Two-Channel Self-Attention Mechanism
Song, Yan-Tao
Lu, Yun-Li
Tien Tzu Hsueh Pao/Acta Electronica Sinica, 2024, 52 (11): : 3835 - 3846
[26] SN-FPN: Self-Attention Nested Feature Pyramid Network for Digital Pathology Image Segmentation
Lee, Sanghoon
Aminul Islam, Kazi
Chandana Koganti, Sai
Yaganti, Varshini
Ramya Sri Mamillapalli, Sai
Vitalos, Hannah
Williamson, Drew F. K.
IEEE ACCESS, 2024, 12 : 92764 - 92773
[27] VSmTrans: A hybrid paradigm integrating self-attention and convolution for 3D medical image segmentation
Liu, Tiange
Bai, Qingze
Torigian, Drew A.
Tong, Yubing
Udupa, Jayaram K.
MEDICAL IMAGE ANALYSIS, 2024, 98
[28] SAU-Net: Medical Image Segmentation Method Based on U-Net and Self-Attention
Zhang S.-J.
Peng Z.
Li H.
Tien Tzu Hsueh Pao/Acta Electronica Sinica, 2022, 50 (10): : 2433 - 2442
[29] Multi-Scale Self-Guided Attention for Medical Image Segmentation
Sinha, Ashish
Dolz, Jose
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2021, 25 (01) : 121 - 130
[30] CSAP-UNet: Convolution and self-attention paralleling network for medical image segmentation with edge enhancement
Fan X.
Zhou J.
Jiang X.
Xin M.
Hou L.
Computers in Biology and Medicine, 2024, 172

← 1 2 3 4 5 →