Abstract
Convolutional neural networks have presented a new paradigm in the field of computer vision, but their fixed convolutional filter size causes long-range dependency loss problems. Also, because of the equal importance of all convolution filters, unnecessary information is included in the convolution result. These problems are more serious in image segmentation, where every pixel is labeled, as opposed to image classification or object recognition. In this paper, to alleviate these problems, we propose an attention-based neural network block that extracts robust features including channel and spatial information. The proposed block calculates the pixel relationship on a unit channel and then calculates the importance among channels. To evaluate the effectiveness of the proposed blocks, we constructed segmentation models by applying the proposed blocks to well-known network and measures their segmentation accuracy. We report some of the results.
Original language | English |
---|---|
Title of host publication | Proceedings - 2022 IEEE International Conference on Big Data and Smart Computing, BigComp 2022 |
Editors | Herwig Unger, Young-Kuk Kim, Eenjun Hwang, Sung-Bae Cho, Stephan Pareigis, Kyamakya Kyandoghere, Young-Guk Ha, Jinho Kim, Atsuyuki Morishima, Christian Wagner, Hyuk-Yoon Kwon, Yang-Sae Moon, Carson Leung |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 246-250 |
Number of pages | 5 |
ISBN (Electronic) | 9781665421973 |
DOIs | |
Publication status | Published - 2022 |
Event | 2022 IEEE International Conference on Big Data and Smart Computing, BigComp 2022 - Daegu, Korea, Republic of Duration: 2022 Jan 17 → 2022 Jan 20 |
Publication series
Name | Proceedings - 2022 IEEE International Conference on Big Data and Smart Computing, BigComp 2022 |
---|
Conference
Conference | 2022 IEEE International Conference on Big Data and Smart Computing, BigComp 2022 |
---|---|
Country/Territory | Korea, Republic of |
City | Daegu |
Period | 22/1/17 → 22/1/20 |
Bibliographical note
Funding Information:ACKNOWLEDGMENT This work was supported by the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIT)(No. NRF-2021R1A4A1031864)
Publisher Copyright:
© 2022 IEEE.
Keywords
- Attention mechanism
- Convolutional Neural Networks
- Feature extraction
- Image segmentation
ASJC Scopus subject areas
- Artificial Intelligence
- Computer Science Applications
- Computer Vision and Pattern Recognition
- Information Systems and Management
- Health Informatics